© 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. 9007
    Prev
    Next
    INDEX
    Explanations

    actions or transitions in a sequence

    oai_token-act-pair · gpt-3.5-turbo

    references to personal experiences and activities

    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
     harms
    -0.71
     Plaint
    -0.64
    cedes
    -0.64
    uffs
    -0.63
     us
    -0.61
    prev
    -0.59
     flows
    -0.58
    inals
    -0.57
    osion
    -0.56
     suits
    -0.56
    POSITIVE LOGITS
     myself
    1.31
     noticing
    1.18
     wondering
    1.12
     researching
    1.10
     thinking
    0.98
     noticed
    0.98
     realize
    0.96
     discovering
    0.96
     realise
    0.95
     curious
    0.94
    Activations Density 0.346%

    No Known Activations