© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11327
    Prev
    Next
    INDEX
    Explanations

    phrases indicating potential actions or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements and hypothetical situations

    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
     Named
    -0.66
    noticed
    -0.63
     Cosponsors
    -0.57
     TIM
    -0.57
     Xuan
    -0.56
     Gladiator
    -0.56
     psy
    -0.55
    named
    -0.55
    eyed
    -0.55
    standing
    -0.55
    POSITIVE LOGITS
     require
    1.11
     ideally
    1.10
     be
    1.06
     entail
    1.05
     imply
    1.05
     suffice
    0.99
     allow
    0.99
     likely
    0.97
     involve
    0.97
     presumably
    0.96
    Activations Density 0.154%

    No Known Activations