© 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. 9-RES-JB
    11. 15366
    Prev
    Next
    INDEX
    Explanations

    words related to processes or plans

    oai_token-act-pair · gpt-3.5-turbo

    terms related to processes and planning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    姫
    -0.81
    ãģĦ
    -0.77
    APTER
    -0.74
    thumbnails
    -0.74
    POSE
    -0.72
    ãĥ©ãĥ³
    -0.72
    士
    -0.71
    ãĥīãĥ©
    -0.69
    ITNESS
    -0.67
    ãĤ¤ãĥĪ
    -0.65
    POSITIVE LOGITS
     for
    0.73
    undown
    0.71
     Opportunity
    0.62
     Canter
    0.62
    emo
    0.60
     Scientology
    0.60
    backs
    0.60
    uggest
    0.59
     pertaining
    0.59
    heet
    0.58
    Activations Density 0.449%

    No Known Activations