© 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. 1-RES-JB
    11. 16822
    Prev
    Next
    INDEX
    Explanations

    mentions of intellectual property

    oai_token-act-pair · gpt-3.5-turbo

    references to intellectual property

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aver
    -0.94
    avers
    -0.86
     decorated
    -0.68
    Patch
    -0.67
    OTA
    -0.66
    annis
    -0.66
    GV
    -0.64
    ICA
    -0.63
    drops
    -0.63
    abb
    -0.63
    POSITIVE LOGITS
    ellectual
    1.30
     intellectual
    1.20
     curiosity
    0.86
     dishon
    0.85
     minds
    0.79
     arte
    0.77
    itialized
    0.76
     philos
    0.76
    ademic
    0.75
    minded
    0.74
    Activations Density 0.008%

    No Known Activations