© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 7717
    Prev
    Next
    INDEX
    Explanations

    mentions of similarities between fictional characters

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    872
    +0.09
    0.3%
    184
    +0.08
    0.2%
    114
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    310
    +0.09
    0.02
    1968
    +0.08
    0.02
    804
    +0.07
    0.03
    Negative Logits
     Hano
    -0.59
     Loreto
    -0.56
     Olimpia
    -0.56
     Fulda
    -0.55
     Alfons
    -0.54
     Constan
    -0.54
     Ancona
    -0.53
    calaure
    -0.53
     Ruman
    -0.52
     Heeren
    -0.52
    POSITIVE LOGITS
     similar
    1.25
    similar
    1.19
     comparable
    1.12
     resemble
    1.10
    Similar
    1.07
     resemblance
    1.06
     analogous
    1.05
     similarity
    1.04
     similarities
    1.03
     resembles
    1.02
    Activations Density 0.420%

    No Known Activations