© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 16379
    Prev
    Next
    INDEX
    Explanations

    phrases indicating some kind of purpose or intention behind an action

    oai_token-act-pair · gpt-3.5-turbo

    phrases that suggest intentions or actions aimed at achieving a particular outcome

    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
    said
    -0.67
    listed
    -0.67
    calling
    -0.67
     Appears
    -0.66
     Orange
    -0.66
    cuts
    -0.65
     Typ
    -0.65
    checked
    -0.63
     Steps
    -0.63
    wrote
    -0.63
    POSITIVE LOGITS
     maximize
    1.52
     minimize
    1.44
     facilitate
    1.42
     achieve
    1.39
     preserve
    1.35
     fulfill
    1.31
     promote
    1.31
     conserve
    1.31
     improve
    1.28
     simplify
    1.27
    Activations Density 0.089%

    No Known Activations