© 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. 0-RES-JB
    11. 7924
    Prev
    Next
    INDEX
    Explanations

    words related to cognitive processes

    oai_token-act-pair · gpt-3.5-turbo

    references to cognitive processes and abilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XXX
    -0.82
     Hood
    -0.75
    rero
    -0.69
    endor
    -0.69
    xxx
    -0.69
    rea
    -0.69
     hose
    -0.68
     Vend
    -0.68
    Raw
    -0.67
    Factory
    -0.67
    POSITIVE LOGITS
     cognitive
    3.30
     Cognitive
    2.80
    ognitive
    2.24
     cognition
    2.24
     neurological
    1.79
     neurolog
    1.75
     behavioral
    1.72
     neuro
    1.63
     behavioural
    1.63
     perceptual
    1.58
    Activations Density 0.022%

    No Known Activations