© 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. 10-RES-JB
    11. 14166
    Prev
    Next
    INDEX
    Explanations

    phrases related to the impact or significance of specific actions or events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to significant impact or effects on various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ĥ¬
    -0.65
    atts
    -0.65
    sbm
    -0.64
    adobe
    -0.63
    wagen
    -0.62
    Tri
    -0.59
     lookout
    -0.59
    Fail
    -0.57
    Vs
    -0.56
    tri
    -0.56
    POSITIVE LOGITS
     upon
    0.96
     shaping
    0.91
     ripple
    0.91
     affecting
    0.91
     on
    0.90
     impacting
    0.89
     negatively
    0.89
     multiplier
    0.84
    ful
    0.83
     whatsoever
    0.83
    Activations Density 0.090%

    No Known Activations