© 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. 3-RES-JB
    11. 1705
    Prev
    Next
    INDEX
    Explanations

    the word "spot" followed by a number indicating intensity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "spot" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    issance
    -0.89
    yss
    -0.72
     rall
    -0.71
    RR
    -0.71
     adolesc
    -0.68
    aughter
    -0.64
     Strait
    -0.64
     godd
    -0.59
    ãĥ¼ãĥĨãĤ£
    -0.59
     ransom
    -0.58
    POSITIVE LOGITS
    lights
    1.28
    eele
    0.91
     spot
    0.89
    ting
    0.88
    lighting
    0.87
     spots
    0.85
    codes
    0.84
    ter
    0.81
    bos
    0.81
    light
    0.80
    Activations Density 0.020%

    No Known Activations