© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 9646
    Prev
    Next
    INDEX
    Explanations

    phrases related to exaggeration and alarmism

    oai_token-act-pair · gpt-3.5-turbo

    expressions of exaggeration and social critique

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

    No Comments

    Negative Logits
     GOODMAN
    -0.74
    URA
    -0.73
    emetery
    -0.70
    foreseen
    -0.69
    onga
    -0.68
    oother
    -0.65
    chrom
    -0.64
     cryst
    -0.63
    JO
    -0.62
     bonding
    -0.62
    POSITIVE LOGITS
     uttered
    1.05
     nonsense
    1.02
     spew
    0.96
     obfusc
    0.95
     excuses
    0.94
     hypoc
    0.92
     excuse
    0.91
     rhetoric
    0.90
     clich
    0.90
     hypocrisy
    0.87
    Activations Density 0.235%

    No Known Activations