© 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. 20019
    Prev
    Next
    INDEX
    Explanations

    terms related to being supportive or providing support to someone or something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to supportiveness or encouragement

    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
    cell
    -0.70
    idation
    -0.69
    liam
    -0.68
    mpeg
    -0.67
    orne
    -0.65
    toggle
    -0.65
    mint
    -0.64
    bag
    -0.64
    din
    -0.64
    fly
    -0.64
    POSITIVE LOGITS
    ively
    0.75
    hetical
    0.75
     undermin
    0.73
     enough
    0.73
    theless
    0.68
     thereof
    0.68
    hetically
    0.67
     femin
    0.67
     Strateg
    0.66
    icularly
    0.66
    Activations Density 0.130%

    No Known Activations