© 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. 2-RES-JB
    11. 24085
    Prev
    Next
    INDEX
    Explanations

    additional or supplementary information

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce supplementary information or add context

    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
    76561
    -0.76
    enders
    -0.72
    olding
    -0.70
    awar
    -0.70
     Fare
    -0.69
    mos
    -0.66
    ender
    -0.66
    Sil
    -0.62
    agers
    -0.61
     Roses
    -0.60
    POSITIVE LOGITS
    æ©Ł
    0.83
     guiActiveUn
    0.73
    atility
    0.71
    theless
    0.66
    ommel
    0.66
    VPN
    0.64
    Reviewed
    0.64
    ificantly
    0.63
    igible
    0.63
    ":["
    0.63
    Activations Density 0.015%

    No Known Activations