© 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. 10073
    Prev
    Next
    INDEX
    Explanations

    the word "medium" in relation to intensity or size

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "medium" and its related context

    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
    çīĪ
    -0.90
    ä½ľ
    -0.86
    ãĤ¼
    -0.77
    alog
    -0.76
     Merch
    -0.75
    atche
    -0.75
    arium
    -0.75
     Masquerade
    -0.72
     Jenner
    -0.70
    é»Ĵ
    -0.69
    POSITIVE LOGITS
     sized
    1.07
    weights
    0.85
    intendent
    0.81
    medium
    0.80
    haired
    0.75
    achusetts
    0.72
     bod
    0.72
     concentrations
    0.71
    rity
    0.70
     humanoid
    0.70
    Activations Density 0.025%

    No Known Activations