© 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. 1-RES-JB
    11. 3291
    Prev
    Next
    INDEX
    Explanations

    occurrences of the abbreviation "MS" along with some numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to Multiple Sclerosis (MS) and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ========
    -0.69
    ãĤ©
    -0.66
     Judaism
    -0.63
     Hundred
    -0.61
    tained
    -0.60
     recalling
    -0.60
     joking
    -0.59
     Strauss
    -0.58
     communist
    -0.56
    ============
    -0.55
    POSITIVE LOGITS
    erver
    1.02
    ertodd
    0.99
    gt
    0.97
    mith
    0.92
    ettings
    0.90
    fw
    0.87
    MS
    0.85
    clerosis
    0.84
    ession
    0.83
    ync
    0.82
    Activations Density 0.005%

    No Known Activations