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. 23
    Prev
    Next
    INDEX
    Explanations

    phrases indicating accessibility to the public

    oai_token-act-pair · gpt-3.5-turbo

    references to accessibility for the public

    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
    å¦
    -0.71
    ardy
    -0.69
    urga
    -0.63
    antz
    -0.63
     doomed
    -0.62
    ously
    -0.61
     Slug
    -0.61
    Dur
    -0.60
     à¤
    -0.60
     dearly
    -0.60
    POSITIVE LOGITS
     outsiders
    0.86
     interpretation
    0.85
     everyone
    0.82
     accommodate
    0.81
     explore
    0.81
     independents
    0.81
     everybody
    0.80
     anyone
    0.77
     entrants
    0.77
     scrutiny
    0.77
    Activations Density 0.128%

    No Known Activations