© 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. 8-RES-JB
    11. 23389
    Prev
    Next
    INDEX
    Explanations

    dates (specifically formatted as dd.mm.yyyy) mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    the presence of specific named entities or characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alist
    -0.74
    iferation
    -0.71
    daq
    -0.68
    definition
    -0.67
    iners
    -0.67
    pmwiki
    -0.66
     divest
    -0.65
     srfAttach
    -0.64
     circulation
    -0.64
     unification
    -0.64
    POSITIVE LOGITS
     POV
    0.86
     Bravo
    0.73
     Bron
    0.73
     Sawyer
    0.72
     Garage
    0.72
     eldest
    0.71
     Wash
    0.71
     Pupp
    0.71
    Compan
    0.70
     Nose
    0.70
    Activations Density 0.336%

    No Known Activations