© 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. 8-RES-JB
    11. 20176
    Prev
    Next
    INDEX
    Explanations

    web addresses and email addresses

    oai_token-act-pair · gpt-3.5-turbo

    sentences ending with a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     basis
    -0.64
     architectural
    -0.64
     attraction
    -0.62
    ħĭ
    -0.61
     sadly
    -0.60
     backward
    -0.60
     backwards
    -0.59
     trophy
    -0.59
    onga
    -0.58
     cod
    -0.58
    POSITIVE LOGITS
    edu
    1.05
    com
    0.93
    tv
    0.90
    tumblr
    0.83
    twitter
    0.82
    blogspot
    0.82
    php
    0.81
    co
    0.80
    push
    0.80
    net
    0.79
    Activations Density 0.111%

    No Known Activations