© 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. 3-RES-JB
    6. 11946
    Prev
    Next
    INDEX
    Explanations

    political and social topics or concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political and social structures or issues

    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
    SN
    -0.69
    nen
    -0.66
    yss
    -0.64
     original
    -0.60
    reditary
    -0.60
    cedented
    -0.59
    7601
    -0.59
     swat
    -0.59
     yawn
    -0.58
    imar
    -0.58
    POSITIVE LOGITS
    atures
    0.73
    ombat
    0.72
    rities
    0.71
    mble
    0.67
    aeda
    0.66
    ontent
    0.65
    erity
    0.61
    tones
    0.61
    Newsletter
    0.60
    smanship
    0.60
    Activations Density 0.712%

    No Known Activations