© 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. 9-RES-JB
    11. 2395
    Prev
    Next
    INDEX
    Explanations

    words related to requirements or conditions that need to be met for something to happen or be successful

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating purpose or necessity initiated by "to"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Caller
    -0.63
    Downloadha
    -0.57
     fue
    -0.57
    monster
    -0.56
    Products
    -0.56
     fractions
    -0.56
     blocks
    -0.55
     newsp
    -0.55
     Ambro
    -0.55
     Brach
    -0.54
    POSITIVE LOGITS
     succeed
    1.13
     thrive
    1.06
     flourish
    1.04
     realize
    1.01
     survive
    1.00
     overcome
    1.00
     decide
    0.99
     partake
    0.99
     be
    0.99
     become
    0.98
    Activations Density 0.144%

    No Known Activations