© 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. 9433
    Prev
    Next
    INDEX
    Explanations

    strong emotional words and physical actions

    oai_token-act-pair · gpt-3.5-turbo

    words that have a "j" sound followed by specific vowel patterns or consonants

    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
    avorite
    -0.76
    sufficient
    -0.74
    ãĤª
    -0.72
    etheless
    -0.62
     Reps
    -0.62
     srfAttach
    -0.60
     predec
    -0.59
     scarce
    -0.58
    minecraft
    -0.56
    uity
    -0.55
    POSITIVE LOGITS
    neys
    0.94
    ansen
    0.71
     Marriott
    0.70
    ney
    0.69
    lin
    0.68
    anic
    0.67
    dan
    0.66
    ournal
    0.66
    unal
    0.65
    atl
    0.65
    Activations Density 0.168%

    No Known Activations