© 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. 6135
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce information or present conclusions

    oai_token-act-pair · gpt-3.5-turbo

    clauses or phrases that introduce defining characteristics or explanations

    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
    ugu
    -0.76
    aq
    -0.73
    oug
    -0.64
    iq
    -0.63
    ahime
    -0.63
    UG
    -0.61
    ablish
    -0.59
    MQ
    -0.59
    roying
    -0.58
    hent
    -0.58
    POSITIVE LOGITS
     horr
    1.14
     extends
    0.94
     accompanies
    0.90
     ought
    0.89
     encompasses
    0.89
     haun
    0.87
     culmin
    0.86
     echoes
    0.86
     coincides
    0.85
     occurs
    0.85
    Activations Density 0.145%

    No Known Activations