Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 6653
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and programming terms

    oai_token-act-pair · gpt-3.5-turbo

    mathematical or programming expressions and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.76
    indust
    -0.71
     Opportun
    -0.64
     invitations
    -0.64
    tin
    -0.61
     Announce
    -0.61
    international
    -0.60
     USPS
    -0.60
    certain
    -0.59
     solicit
    -0.59
    POSITIVE LOGITS
    seq
    0.76
    args
    0.76
    uments
    0.75
     =>
    0.74
     })
    0.73
     ->
    0.72
     theorem
    0.71
    ptr
    0.70
    orial
    0.68
     nucleus
    0.68
    Activations Density 0.122%

    No Known Activations