© 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. 14793
    Prev
    Next
    INDEX
    Explanations

    words that start with 'Z' followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'Z'

    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
    tenance
    -0.74
    ãĥ¼ãĥĨ
    -0.72
    ãĥ¼ãĥĨãĤ£
    -0.72
     Lauder
    -0.68
    espie
    -0.68
     Scots
    -0.67
     spirited
    -0.66
     totality
    -0.65
    ãĥĩãĤ£
    -0.65
    tainment
    -0.64
    POSITIVE LOGITS
    ERO
    1.21
    ebra
    1.20
    odiac
    1.10
    eros
    1.02
    ombies
    0.97
    ymes
    0.97
    immer
    0.97
    ombie
    0.96
    ither
    0.96
    ulu
    0.96
    Activations Density 0.025%

    No Known Activations