© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7595
    Prev
    Next
    INDEX
    Explanations

    adjectives or nouns related to physical objects that are able to be touched or perceived visually

    oai_token-act-pair · gpt-3.5-turbo

    references to tangible outcomes or effects

    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
    cker
    -0.81
    kers
    -0.71
    alian
    -0.68
    ologies
    -0.67
    annis
    -0.67
    oan
    -0.67
    giene
    -0.67
    oly
    -0.66
    ften
    -0.66
    hov
    -0.66
    POSITIVE LOGITS
     tangible
    1.01
     manifestation
    0.84
    isable
    0.83
     defic
    0.82
    izable
    0.79
    itarian
    0.78
     conclud
    0.76
    aneously
    0.76
    zx
    0.74
    TY
    0.73
    Activations Density 0.016%

    No Known Activations