Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 8045
    Prev
    Next
    INDEX
    Explanations

    words related to computer programming pointers and handlers

    oai_token-act-pair · gpt-3.5-turbo

    terms related to pointers and memory management in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aram
    -0.87
    arus
    -0.83
    agall
    -0.81
    iary
    -0.74
    orian
    -0.74
    uate
    -0.73
    arine
    -0.73
    oro
    -0.72
    abul
    -0.72
    amorph
    -0.70
    POSITIVE LOGITS
    ////////
    0.88
     ptr
    0.76
    ATURE
    0.74
    CHR
    0.71
    -+-+-+-+
    0.70
    Reloaded
    0.68
     pointer
    0.68
    TEXT
    0.66
    IUM
    0.66
    verted
    0.66
    Activations Density 0.044%

    No Known Activations