Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 9111
    Prev
    Next
    INDEX
    Explanations

    phrases related to achievement or progress

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating reaching a certain level or milestone

    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
     preceded
    -0.68
     accompanies
    -0.68
    oir
    -0.66
     followed
    -0.61
    sbm
    -0.61
     Seym
    -0.61
     includ
    -0.59
     replaced
    -0.58
     accompanied
    -0.58
     accompanying
    -0.58
    POSITIVE LOGITS
     milestone
    1.44
     conclusion
    1.29
     milestones
    1.24
     threshold
    1.23
     heights
    1.20
     climax
    1.15
     plateau
    1.15
     pinnacle
    1.13
     goal
    1.11
     tipping
    1.10
    Activations Density 0.218%

    No Known Activations