Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 548
    Prev
    Next
    INDEX
    Explanations

    medical conditions related to the spine, such as spinal fluid leaking, lumbar drain, spinal cord issues, and back pain

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.15
    0.6%
    1805
    +0.12
    0.5%
    893
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1805
    +0.15
    0.03
    1385
    +0.12
    0.04
    1363
    +0.11
    0.02
    Negative Logits
    <bos>
    -1.70
     intersper
    -1.19
     encomp
    -1.18
     coar
    -1.15
     unve
    -1.10
     reconno
    -1.08
     disreg
    -1.04
     volunte
    -1.03
     unce
    -1.01
     scrat
    -1.00
    POSITIVE LOGITS
     spinal
    1.15
     spine
    1.13
    spinal
    1.05
    Spine
    0.97
     Spine
    0.97
     Spinal
    0.91
    spine
    0.82
     spines
    0.71
    ylül
    0.66
    ropractor
    0.65
    Activations Density 0.236%

    No Known Activations