© 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. 4-RES-JB
    11. 17029
    Prev
    Next
    INDEX
    Explanations

    phrases that suggest potential negative outcomes or consequences

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating results or consequences of actions

    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
    aeper
    -0.75
    kt
    -0.70
    ian
    -0.69
    ault
    -0.65
    ramid
    -0.64
    atu
    -0.63
    ilings
    -0.63
    aredevil
    -0.63
     Quart
    -0.62
     Technique
    -0.62
    POSITIVE LOGITS
     cele
    1.08
     havoc
    0.86
     irre
    0.78
     trouble
    0.77
    ãĥĨãĤ£
    0.75
     undue
    0.74
    heat
    0.69
    facts
    0.69
    cause
    0.68
     nightmares
    0.67
    Activations Density 0.025%

    No Known Activations