© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    11. 11930
    Prev
    Next
    INDEX
    Explanations

    unique identifiers or keywords likely corresponding to specific entities or objects mentioned in the text, possibly in a context related to media, organizations, or politics

    oai_token-act-pair · gpt-3.5-turbo

    references to specific people or entities associated with an "Os" designation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vent
    -0.66
     railing
    -0.65
     sponge
    -0.65
     allergy
    -0.61
     Grind
    -0.60
     BuzzFeed
    -0.60
     Brend
    -0.59
     vent
    -0.59
     chill
    -0.59
     masturbation
    -0.58
    POSITIVE LOGITS
    Os
    4.69
     Os
    1.70
    Es
    1.63
    O
    1.58
    Ts
    1.39
    Ds
    1.36
    Ps
    1.26
    Ns
    1.21
    Cs
    1.21
    Gs
    1.19
    Activations Density 0.010%

    No Known Activations