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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 10776
    Prev
    Next
    INDEX
    Explanations

    names or keywords related to a person, possibly a figure in contemporary media or politics

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or proper names in the context of a campaign or news

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ðĿ
    -0.76
    share
    -0.73
    REC
    -0.68
     chilling
    -0.67
    dropping
    -0.66
    Ms
    -0.66
     defe
    -0.66
    Save
    -0.65
    IVE
    -0.65
    IBLE
    -0.65
    POSITIVE LOGITS
    igans
    1.27
    kees
    1.23
    yan
    1.15
    onymous
    1.07
    athan
    0.98
    aun
    0.92
    ous
    0.86
    osuke
    0.85
    omon
    0.84
    nan
    0.83
    Activations Density 0.007%

    No Known Activations