© 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. 8-RES-JB
    11. 10796
    Prev
    Next
    INDEX
    Explanations

    words related to harm and destruction

    oai_token-act-pair · gpt-3.5-turbo

    terms related to harmful or destructive effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aintain
    -0.90
    illon
    -0.81
    ĸļ
    -0.79
    ailable
    -0.78
    famous
    -0.76
    quart
    -0.75
    ucket
    -0.73
    ains
    -0.73
    ailed
    -0.72
    avia
    -0.72
    POSITIVE LOGITS
     tendencies
    0.89
    ly
    0.87
     impulses
    0.83
     combination
    0.82
     nature
    0.81
     alien
    0.81
     behaviour
    0.80
     substances
    0.80
     consequences
    0.79
     implication
    0.79
    Activations Density 0.137%

    No Known Activations