© 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. 5039
    Prev
    Next
    INDEX
    Explanations

    phrases related to social or political commentary

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating collective actions or opinions of people

    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
     predecessor
    -0.98
     srfAttach
    -0.77
     successor
    -0.71
     competitor
    -0.70
     predecessors
    -0.65
     counterpart
    -0.65
    xton
    -0.65
    iator
    -0.64
    Accessory
    -0.64
     candidacy
    -0.63
    POSITIVE LOGITS
     clam
    1.13
     grav
    0.85
     misinterpret
    0.83
     understandably
    0.76
     smarter
    0.74
     mouths
    0.72
     gull
    0.71
    NetMessage
    0.71
     starving
    0.71
     underestimate
    0.71
    Activations Density 0.264%

    No Known Activations