Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 9215
    Prev
    Next
    INDEX
    Explanations

    words related to cybersecurity and hacking

    oai_token-act-pair · gpt-3.5-turbo

    terms related to security, hacking, and technical jargon

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yond
    -0.89
     carbohyd
    -0.87
    icter
    -0.81
     satell
    -0.78
     princess
    -0.77
    alysed
    -0.76
     srf
    -0.76
    ahon
    -0.75
    itled
    -0.75
    bably
    -0.74
    POSITIVE LOGITS
     Association
    1.25
     Prevention
    1.21
     Index
    1.18
     Disorder
    1.16
     Removal
    1.13
     Strategies
    1.12
     Syndrome
    1.12
     Database
    1.11
     Programs
    1.11
     Relationship
    1.11
    Activations Density 0.319%

    No Known Activations