© 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. 3-RES-JB
    11. 2793
    Prev
    Next
    INDEX
    Explanations

    phrases indicating support or alignment towards a particular position or group

    oai_token-act-pair · gpt-3.5-turbo

    references to different sides in a debate or conflict

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    initions
    -0.85
    iott
    -0.80
    ciating
    -0.77
    ãĤ¼ãĤ¦ãĤ¹
    -0.73
    yssey
    -0.72
    ctory
    -0.71
    issance
    -0.70
    untu
    -0.70
    ESCO
    -0.69
    ãģ®éŃĶ
    -0.67
    POSITIVE LOGITS
    side
    0.97
     side
    0.96
     Side
    0.91
    kick
    0.83
    Side
    0.76
     Za
    0.72
     Kl
    0.71
     seams
    0.69
     sides
    0.68
     plank
    0.67
    Activations Density 0.025%

    No Known Activations