© 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. 10-RES-JB
    11. 11080
    Prev
    Next
    INDEX
    Explanations

    proper names or handles related to social media

    oai_token-act-pair · gpt-3.5-turbo

    mentions of social media usernames and websites

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Scheme
    -0.95
     Pipeline
    -0.83
     Boo
    -0.83
     Directive
    -0.79
     Enabled
    -0.78
     Wa
    -0.78
     Healer
    -0.77
     Amnesty
    -0.76
     Singer
    -0.76
     Inspection
    -0.75
    POSITIVE LOGITS
    isoft
    1.22
    ifax
    1.22
    iverpool
    1.18
    yp
    1.17
    arcity
    1.13
    yond
    1.10
    internet
    1.10
    entin
    1.10
    erc
    1.07
    iem
    1.06
    Activations Density 0.104%

    No Known Activations