© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 23683
    Prev
    Next
    INDEX
    Explanations

    names or identifiers within code snippets

    oai_token-act-pair · gpt-3.5-turbo

    terms related to naming conventions in programming or data structures

    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
    emonium
    -0.77
    avorite
    -0.73
    senal
    -0.72
    yrus
    -0.72
     masturbation
    -0.72
     simul
    -0.70
     instructional
    -0.68
    ĸļ
    -0.68
    ropolis
    -0.67
     economical
    -0.67
    POSITIVE LOGITS
    ='
    1.04
    ="
    0.98
    name
    0.92
    =""
    0.90
    Name
    0.90
     ==
    0.89
    :'
    0.88
     !=
    0.85
     Unknown
    0.85
    ("
    0.84
    Activations Density 0.066%

    No Known Activations