© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 421
    Prev
    Next
    INDEX
    Explanations

    references to the state of Iowa

    oai_token-act-pair · gpt-3.5-turbo

    references to the state of Iowa

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

    No Comments

    Negative Logits
     warr
    -0.92
    edom
    -0.81
    */(
    -0.77
    ecast
    -0.74
    Oracle
    -0.74
    estyles
    -0.74
    âĶĢâĶĢ
    -0.71
    essage
    -0.68
    henko
    -0.67
     certs
    -0.66
    POSITIVE LOGITS
     Rapids
    1.09
    Iowa
    1.07
     Iowa
    1.06
     Caucus
    0.96
     State
    0.87
     caucuses
    0.87
    keye
    0.86
    keyes
    0.85
     caucus
    0.84
    ansas
    0.84
    Activations Density 0.008%

    No Known Activations