© 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. 6401
    Prev
    Next
    INDEX
    Explanations

    words related to investigation, close examination, or critical assessment

    oai_token-act-pair · gpt-3.5-turbo

    mentions of scrutiny or critical examination

    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
    thus
    -0.80
    tein
    -0.71
    stead
    -0.71
    tre
    -0.66
    activated
    -0.65
    activate
    -0.65
    jc
    -0.65
    Hero
    -0.64
    iot
    -0.63
    lua
    -0.61
    POSITIVE LOGITS
     scrutiny
    1.31
     scrutin
    0.94
    é¾įå¥ij士
    0.89
     Probe
    0.87
     probing
    0.82
    ively
    0.79
    wcsstore
    0.76
     questions
    0.75
     probes
    0.75
    dogs
    0.74
    Activations Density 0.011%

    No Known Activations