© 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. 8-RES-JB
    11. 2706
    Prev
    Next
    INDEX
    Explanations

    references to the word "Del" followed by a numerical value

    oai_token-act-pair · gpt-3.5-turbo

    the word "Del" in various contexts

    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
     Moonlight
    -0.70
    SHIP
    -0.69
     AFL
    -0.66
    OLOGY
    -0.64
    beans
    -0.61
     FTA
    -0.60
     CPI
    -0.58
     OPS
    -0.58
     Jinn
    -0.58
    finder
    -0.57
    POSITIVE LOGITS
    ayed
    1.30
    phi
    1.26
    usional
    1.20
    icate
    1.19
    aware
    1.16
    ivery
    1.15
    ivered
    1.14
    ivering
    1.14
    iber
    1.09
    inqu
    1.09
    Activations Density 0.020%

    No Known Activations