© 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. 11135
    Prev
    Next
    INDEX
    Explanations

    words related to expressing an auditory experience

    oai_token-act-pair · gpt-3.5-turbo

    expressions of opinion or judgment about various topics

    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
    odder
    -0.72
     Lann
    -0.71
    apsed
    -0.70
    isec
    -0.63
    uve
    -0.62
    udeau
    -0.62
    rient
    -0.61
    keye
    -0.60
     Janeiro
    -0.60
    keyes
    -0.60
    POSITIVE LOGITS
    Sounds
    1.01
    tracks
    0.91
     sounds
    0.89
     Sounds
    0.89
     sounded
    0.87
    sound
    0.83
     noises
    0.82
     sounding
    0.82
    tones
    0.81
    checks
    0.81
    Activations Density 0.014%

    No Known Activations