© 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. 3-RES-JB
    11. 8398
    Prev
    Next
    INDEX
    Explanations

    negative adjectives

    oai_token-act-pair · gpt-3.5-turbo

    negative evaluations or consequences

    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
    anwhile
    -0.73
    heny
    -0.72
    iture
    -0.71
    iferation
    -0.69
    orney
    -0.66
     GOODMAN
    -0.65
    eer
    -0.64
    án
    -0.64
    ership
    -0.64
    ynthesis
    -0.63
    POSITIVE LOGITS
     behaved
    0.86
     enough
    0.84
     suited
    0.79
     damaged
    0.77
    asses
    0.77
     beaten
    0.75
     patched
    0.72
     degraded
    0.71
     wounded
    0.70
    enough
    0.69
    Activations Density 0.009%

    No Known Activations