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

    Neuronpedia

    APICircuit 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. 6144
    Prev
    Next
    INDEX
    Explanations

    sentences with a combination of specific verbs and pronouns

    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
    1892
    +0.11
    0.5%
    1334
    +0.10
    0.4%
    994
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    24
    +0.11
    0.11
    1776
    +0.10
    0.09
    1334
    +0.10
    0.08
    Negative Logits
    <bos>
    -2.47
    .
    -0.66
    ,
    -0.60
     кло
    -0.54
    ?
    -0.53
     (
    -0.53
     launched
    -0.52
    :
    -0.52
     established
    -0.52
     revealed
    -0.51
    POSITIVE LOGITS
     maroc
    1.26
     bandung
    1.24
     affez
    1.23
     ananas
    1.18
     cioc
    1.16
     sentra
    1.11
     venuto
    1.09
     ristor
    1.07
     kokos
    1.06
     swarovski
    1.05
    Activations Density 6.050%

    No Known Activations