© 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. 6-RES-JB
    11. 20488
    Prev
    Next
    INDEX
    Explanations

    phrases related to harmful or destructive elements

    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 @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    illon
    -0.88
    buck
    -0.84
    rows
    -0.82
    ords
    -0.81
    quart
    -0.80
    peak
    -0.77
    cedented
    -0.77
    ailable
    -0.77
    eah
    -0.76
    aintain
    -0.75
    POSITIVE LOGITS
     effects
    0.84
     aft
    0.83
     substances
    0.82
     consequences
    0.79
     harmful
    0.78
     alien
    0.78
     aspects
    0.77
     undermin
    0.77
     tendencies
    0.75
    ãĥ¼ãĥĨ
    0.75
    Activations Density 0.065%

    No Known Activations