© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 6977
    Prev
    Next
    INDEX
    Explanations

    instances of text related to computer programming and pointer management

    oai_token-act-pair · gpt-3.5-turbo

    references to the organization and management of data objects and their states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ogyn
    -0.80
    venants
    -0.73
    abuse
    -0.72
    eni
    -0.70
    nov
    -0.70
    ships
    -0.69
    our
    -0.68
    ËĪ
    -0.68
    igans
    -0.67
    ply
    -0.67
    POSITIVE LOGITS
     desired
    1.51
     specified
    1.43
     corresponding
    1.36
     same
    1.32
     entire
    1.24
     selected
    1.23
     respective
    1.23
     entirety
    1.22
     appropriate
    1.22
     nearest
    1.18
    Activations Density 0.301%

    No Known Activations