© 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. 17543
    Prev
    Next
    INDEX
    Explanations

    mentions of drug overdosing or overwriting

    oai_token-act-pair · gpt-3.5-turbo

    terms related to overdose and its 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
    anwhile
    -0.73
    kie
    -0.69
    MENT
    -0.68
    auga
    -0.68
    =-=-=-=-=-=-=-=-
    -0.67
    Assembly
    -0.66
    andum
    -0.66
    kit
    -0.64
     Dag
    -0.64
     Pupp
    -0.63
    POSITIVE LOGITS
     overd
    1.30
    rawn
    0.92
    rown
    0.89
    raft
    0.88
    ivery
    0.85
    rafted
    0.82
    etermination
    0.80
    icated
    0.77
    irty
    0.77
    olic
    0.76
    Activations Density 0.013%

    No Known Activations