© 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. 11623
    Prev
    Next
    INDEX
    Explanations

    terms related to suspicion or potential risk

    oai_token-act-pair · gpt-3.5-turbo

    references to suspicious behavior or activities

    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
    skill
    -0.82
    ankind
    -0.72
    arf
    -0.72
    unes
    -0.67
    parable
    -0.67
    apsed
    -0.66
    yna
    -0.66
     taught
    -0.65
    jri
    -0.65
    dain
    -0.63
    POSITIVE LOGITS
    ly
    1.20
     suspicious
    0.92
    ively
    0.89
    LY
    0.86
    icious
    0.86
    liness
    0.81
    lys
    0.79
     suspic
    0.78
    uously
    0.77
     Activity
    0.77
    Activations Density 0.023%

    No Known Activations