© 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. 11-RES-JB
    11. 7041
    Prev
    Next
    INDEX
    Explanations

    phrases related to starting or initiating actions

    oai_token-act-pair · gpt-3.5-turbo

    commands and phrases indicating initiation or progression of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KO
    -0.64
    eur
    -0.64
     Donation
    -0.61
    iership
    -0.57
    Uncommon
    -0.56
     Palestin
    -0.56
     Colleges
    -0.55
     Reserv
    -0.55
     Medal
    -0.54
    volent
    -0.54
    POSITIVE LOGITS
     briefly
    0.90
    iterator
    0.84
     ourselves
    0.77
     deeper
    0.77
    reference
    0.76
     straight
    0.74
    izont
    0.72
    technical
    0.71
    into
    0.71
    enda
    0.70
    Activations Density 0.123%

    No Known Activations