© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 17150
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    quotable phrases or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     favor
    -0.76
     bunk
    -0.71
     honor
    -0.71
     nude
    -0.69
     clo
    -0.69
     livestream
    -0.69
     footing
    -0.68
     nested
    -0.67
     encl
    -0.67
     inadequ
    -0.66
    POSITIVE LOGITS
    Therefore
    1.28
    Whereas
    1.27
    It
    1.25
    There
    1.23
    They
    1.22
    If
    1.21
    However
    1.21
    Unless
    1.20
    We
    1.18
    Fortunately
    1.17
    Activations Density 0.092%

    No Known Activations