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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 8324
    Prev
    Next
    INDEX
    Explanations

    words related to operational procedures and technical descriptions, especially those containing the letters 'OW'

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    senal
    -0.70
     gratification
    -0.69
     circulate
    -0.66
    ãĤ¶
    -0.65
     rhet
    -0.61
     forge
    -0.60
     fantas
    -0.59
     chall
    -0.59
     pinch
    -0.58
     apartheid
    -0.58
    POSITIVE LOGITS
    OW
    1.31
    ARDS
    1.19
    HEAD
    1.15
    OWS
    1.11
    LAN
    1.10
    ERS
    1.08
    orld
    1.08
    OOD
    1.06
    DER
    1.06
    BO
    1.05
    Activations Density 0.005%

    No Known Activations