© 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. 4-RES-JB
    11. 10062
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Had" or its slight variations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Had" in various contexts

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

    No Comments

    Negative Logits
    FTWARE
    -0.67
     outp
    -0.64
    IGHTS
    -0.64
    atile
    -0.61
    Ú
    -0.60
    ilings
    -0.60
    ensitive
    -0.59
    Chel
    -0.58
     defense
    -0.57
    essee
    -0.56
    POSITIVE LOGITS
    hers
    0.93
    nesday
    0.89
     been
    0.86
    luck
    0.83
    rien
    0.83
    rons
    0.83
     Been
    0.82
    ibur
    0.82
     undergone
    0.81
     gotten
    0.78
    Activations Density 0.067%

    No Known Activations