© 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. 3-RES-JB
    11. 13590
    Prev
    Next
    INDEX
    Explanations

    references to names or terms starting with "Con"

    oai_token-act-pair · gpt-3.5-turbo

    references to the company Conoco or similar entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uyomi
    -0.76
    Ń·
    -0.67
    terday
    -0.66
    ...]
    -0.66
    ħĭ
    -0.65
    HAEL
    -0.63
    TPS
    -0.63
    loo
    -0.62
     practicable
    -0.60
    anwhile
    -0.60
    POSITIVE LOGITS
    venient
    1.08
    nex
    1.06
    crete
    1.03
    ventions
    1.01
    secut
    0.99
    ceived
    0.95
    ventional
    0.95
    yers
    0.94
    clusions
    0.91
    vict
    0.90
    Activations Density 0.006%

    No Known Activations