© 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. 7-RES-JB
    11. 6481
    Prev
    Next
    INDEX
    Explanations

    information related to an ongoing investigation or search

    oai_token-act-pair · gpt-3.5-turbo

    sentences or phrases indicating ongoing situations or investigations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ollen
    -0.77
     fat
    -0.67
     bound
    -0.66
     furnace
    -0.65
    ween
    -0.65
     enrol
    -0.64
     dungeon
    -0.64
    zzle
    -0.64
    elled
    -0.64
     painfully
    -0.63
    POSITIVE LOGITS
     Regardless
    1.27
     Nevertheless
    1.25
     Nonetheless
    1.25
     Anyway
    1.14
     Therefore
    1.11
     Fortunately
    1.10
     However
    1.10
     Furthermore
    1.09
     Additionally
    1.07
     Moreover
    1.07
    Activations Density 0.750%

    No Known Activations