© 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. 0-RES-JB
    11. 22467
    Prev
    Next
    INDEX
    Explanations

    words related to various forms of information technology

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'v' or the character sequence 'v'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     repatri
    -0.67
     fingert
    -0.59
     slic
    -0.58
     Hicks
    -0.56
     hide
    -0.56
     grooming
    -0.56
     associate
    -0.55
     deduct
    -0.55
     cradle
    -0.55
     Peck
    -0.55
    POSITIVE LOGITS
    v
    3.75
    va
    2.01
    vi
    2.00
    vs
    2.00
    vt
    1.98
    V
    1.90
    vy
    1.86
    viks
    1.83
    vP
    1.82
    vv
    1.82
    Activations Density 0.029%

    No Known Activations