© 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. 5462
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or decisions being taken

    oai_token-act-pair · gpt-3.5-turbo

    references to undefined or ambiguous concepts

    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
     palm
    -0.79
     oven
    -0.78
     barr
    -0.74
     mum
    -0.71
     indemn
    -0.70
     handic
    -0.70
     mail
    -0.70
     Lumpur
    -0.68
     nuts
    -0.68
     pronoun
    -0.68
    POSITIVE LOGITS
    meaning
    1.33
    that
    1.30
    especially
    1.28
    these
    1.28
    perhaps
    1.28
    which
    1.27
    they
    1.26
    particularly
    1.26
    including
    1.24
    feat
    1.23
    Activations Density 0.077%

    No Known Activations