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

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 20327
    Prev
    Next
    INDEX
    Explanations

    words related to visiting or participation in events or activities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "visiting" and related activities involving presence or participation

    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
    yon
    -0.79
    iness
    -0.77
    cms
    -0.76
    ère
    -0.76
    pel
    -0.76
    talk
    -0.76
    oho
    -0.74
    ombat
    -0.73
    ung
    -0.72
    hap
    -0.71
    POSITIVE LOGITS
     exha
    0.85
     behavi
    0.80
     alcoholic
    0.78
    redients
    0.76
     conduc
    0.73
     mosqu
    0.73
    NESS
    0.72
     Pengu
    0.72
     Females
    0.71
     rodents
    0.71
    Activations Density 0.262%

    No Known Activations