© 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. 14125
    Prev
    Next
    INDEX
    Explanations

    phrases or terms that involve written communication or documentation

    oai_token-act-pair · gpt-3.5-turbo

    references to written documentation or formal statements

    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
    tics
    -0.86
    olen
    -0.84
    rir
    -0.81
    aho
    -0.80
    alos
    -0.79
    ertodd
    -0.78
    olit
    -0.78
    alian
    -0.78
    Ĭ±
    -0.76
    alach
    -0.76
    POSITIVE LOGITS
     statement
    1.18
     declaration
    1.12
     explanation
    1.10
     agreement
    1.09
     invitation
    1.09
     apology
    1.09
     acknowledgment
    1.08
     acknowledgement
    1.05
     indication
    1.02
     communication
    1.02
    Activations Density 0.068%

    No Known Activations