© 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. 4-RES-JB
    11. 14857
    Prev
    Next
    INDEX
    Explanations

    email and website addresses

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of web addresses and associated information

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

    No Comments

    Negative Logits
     grounding
    -0.74
     overlooked
    -0.74
     rall
    -0.72
     affirm
    -0.71
     attacker
    -0.70
     glim
    -0.70
     iceberg
    -0.70
     grop
    -0.69
     acquaintance
    -0.69
     behavi
    -0.69
    POSITIVE LOGITS
    com
    1.40
    blogspot
    1.34
    edu
    1.19
    html
    1.16
    php
    1.14
    tumblr
    1.14
    net
    1.12
    htm
    1.11
    jpg
    1.09
    aspx
    1.09
    Activations Density 0.195%

    No Known Activations