© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 5610
    Prev
    Next
    INDEX
    Explanations

    terms related to computer programming and software development

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "de" in various contexts, perhaps indicating a focus on identifiers or designated attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Origins
    -0.83
     Flavoring
    -0.75
    ĸļ
    -0.72
     Atmosp
    -0.71
     Peb
    -0.70
    ORY
    -0.70
     Kinnikuman
    -0.69
     Orbit
    -0.68
    INESS
    -0.68
     HELL
    -0.66
    POSITIVE LOGITS
    ploy
    1.34
    legate
    1.31
    legates
    1.16
    utsche
    1.12
    cember
    1.10
    leted
    1.05
    bris
    1.01
    forestation
    1.00
    hyde
    0.99
    vel
    0.96
    Activations Density 0.005%

    No Known Activations