© 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. 14905
    Prev
    Next
    INDEX
    Explanations

    references to victories or achievements

    oai_token-act-pair · gpt-3.5-turbo

    topics related to political success and challenges

    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
    .).
    -0.66
    ".
    -0.58
    '.
    -0.58
    âĵĺ
    -0.57
    %.
    -0.57
    $.
    -0.56
    instead
    -0.56
    usercontent
    -0.55
    }.
    -0.54
    atever
    -0.54
    POSITIVE LOGITS
     nutshell
    0.51
    pires
    0.49
     depends
    0.45
     )]
    0.44
    ¶
    0.44
     bulletin
    0.42
    ciplinary
    0.41
    otomy
    0.40
     varies
    0.40
    urgical
    0.39
    Activations Density 4.612%

    No Known Activations