© 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. 7-RES-JB
    11. 13394
    Prev
    Next
    INDEX
    Explanations

    information related to subscribing or checking out issues in a publication

    oai_token-act-pair · gpt-3.5-turbo

    invitations and prompts to subscribe or engage with content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fman
    -0.80
    abase
    -0.73
    chard
    -0.69
    orde
    -0.68
    heet
    -0.67
    aterasu
    -0.65
     Azerb
    -0.65
    icient
    -0.65
     Annex
    -0.64
     Chun
    -0.64
    POSITIVE LOGITS
    à¤
    0.81
    ÏĦ
    0.68
     UNHCR
    0.64
    atform
    0.64
    γ
    0.63
    ãĥĪ
    0.63
    Ùħ
    0.62
    à
    0.62
    ulkan
    0.61
    ε
    0.60
    Activations Density 0.038%

    No Known Activations