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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 12155
    Prev
    Next
    INDEX
    Explanations

    phrases related to attitude or demeanor, particularly phrases indicating defiance or readiness for confrontation

    oai_token-act-pair · gpt-3.5-turbo

    references to personal pronouns and possessive forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Guant
    -0.67
    photos
    -0.64
    abilia
    -0.63
     photographed
    -0.60
    vernment
    -0.60
    IUM
    -0.58
     photograp
    -0.57
    cens
    -0.56
     PLUS
    -0.55
    elist
    -0.55
    POSITIVE LOGITS
     teeth
    0.79
     jaws
    0.70
     lips
    0.68
     eyes
    0.68
     pants
    0.68
     Horses
    0.66
    okes
    0.66
     ears
    0.66
     heels
    0.65
     sleeve
    0.62
    Activations Density 0.357%

    No Known Activations