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

    Neuronpedia

    APICircuit 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. 4-RES-JB
    6. 21622
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical environments, structures, and conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to significant attributes or conditions in various contexts

    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
    itars
    -0.82
    urches
    -0.76
    ernels
    -0.74
    nces
    -0.74
    akings
    -0.72
    iences
    -0.72
    rencies
    -0.71
     Hoo
    -0.71
    brids
    -0.70
    ormons
    -0.69
    POSITIVE LOGITS
     standpoint
    0.98
     perspective
    0.76
     environment
    0.75
     handful
    0.73
     colony
    0.71
     batch
    0.68
     footing
    0.68
     altercation
    0.66
     outing
    0.66
     settlement
    0.66
    Activations Density 0.832%

    No Known Activations