© 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. 7-RES-JB
    11. 18738
    Prev
    Next
    INDEX
    Explanations

    terms related to malicious activities or intentions

    oai_token-act-pair · gpt-3.5-turbo

    references to malicious activities or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -1.35
    gdala
    -0.84
    marks
    -0.78
    ĨĴ
    -0.75
    ILA
    -0.75
    arium
    -0.74
    marked
    -0.73
    ills
    -0.73
    hene
    -0.72
    illy
    -0.72
    POSITIVE LOGITS
    ly
    1.24
     intent
    1.07
     mischief
    0.82
     behaviour
    0.81
     activity
    0.81
     payload
    0.80
     behavior
    0.78
     implant
    0.77
    ness
    0.76
     enterprise
    0.76
    Activations Density 0.036%

    No Known Activations