© 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. 19594
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the character 'Ĺ'

    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
    idges
    -0.84
    asonic
    -0.82
     disadvant
    -0.77
     oun
    -0.76
    awar
    -0.75
    ifax
    -0.74
     comprom
    -0.72
    omorphic
    -0.71
     grips
    -0.69
    apping
    -0.69
    POSITIVE LOGITS
    Ĺ
    1.05
    ï¸ı
    0.97
    é»Ĵ
    0.88
    ¤
    0.88
    åĪ
    0.87
    °
    0.86
    æĸ¹
    0.86
    License
    0.85
    lishing
    0.84
    ãĤŃ
    0.83
    Activations Density 0.006%

    No Known Activations