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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8-RES-JB
    6. 15703
    Prev
    Next
    INDEX
    Explanations

    URLs or web links containing 'co'

    oai_token-act-pair · gpt-3.5-turbo

    URLs containing the domain "co."

    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
     ageing
    -0.66
     aging
    -0.61
     minorities
    -0.60
     Lowell
    -0.59
     Norwich
    -0.59
     renovation
    -0.58
     substitutes
    -0.58
     representation
    -0.56
     Grimm
    -0.56
     bases
    -0.56
    POSITIVE LOGITS
    cdn
    0.86
    ffe
    0.76
    verage
    0.75
    ffee
    0.75
    opher
    0.74
    gh
    0.70
    ff
    0.69
    #$
    0.69
    ck
    0.69
    cker
    0.69
    Activations Density 0.006%

    No Known Activations