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. 10-RES-JB
    6. 3769
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of secrecy or concealment

    oai_token-act-pair · gpt-3.5-turbo

    references to "black" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PsyNetMessage
    -0.80
    ASE
    -0.70
    yip
    -0.69
    ICES
    -0.68
    ICLE
    -0.67
    igslist
    -0.67
    Recent
    -0.67
    xon
    -0.66
     Lauder
    -0.66
    afort
    -0.63
    POSITIVE LOGITS
    smith
    1.41
    listed
    1.25
    ened
    1.17
    berry
    1.05
    jack
    1.01
    hawk
    1.00
    berries
    0.99
    face
    0.99
    hole
    0.96
    outs
    0.95
    Activations Density 0.034%

    No Known Activations