© 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. 2-RES-JB
    11. 8429
    Prev
    Next
    INDEX
    Explanations

    terms related to conferences or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "con."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TPS
    -0.76
    terday
    -0.71
    OHN
    -0.71
    Ń·
    -0.69
    İĭ
    -0.63
     wip
    -0.62
     deed
    -0.61
    externalActionCode
    -0.61
     practicable
    -0.60
     hydra
    -0.60
    POSITIVE LOGITS
    stant
    1.16
    ventions
    1.08
    ference
    1.01
    clusions
    0.99
    cept
    0.98
    crete
    0.97
    secut
    0.97
    vention
    0.97
    venient
    0.96
    nex
    0.95
    Activations Density 0.012%

    No Known Activations