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

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 20814
    Prev
    Next
    INDEX
    Explanations

    references to historical figures or texts

    oai_token-act-pair · gpt-3.5-turbo

    the end of a document or text

    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
     interns
    -0.87
     inputs
    -0.84
     backdoor
    -0.81
     TSA
    -0.80
     lasers
    -0.79
     Intercept
    -0.79
     waivers
    -0.78
     monitors
    -0.77
     triggers
    -0.77
     rollout
    -0.77
    POSITIVE LOGITS
    æ
    1.30
    ocrates
    1.25
    û
    1.20
    á¸
    1.18
    â
    1.17
    olkien
    1.15
    akespe
    1.14
    ospels
    1.14
    Å
    1.13
    Åį
    1.11
    Activations Density 0.374%

    No Known Activations