© 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. 16319
    Prev
    Next
    INDEX
    Explanations

    references to projects or initiatives being completed or funded

    oai_token-act-pair · gpt-3.5-turbo

    references to impactful or significant events or actions

    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
    Contents
    -0.75
     reacts
    -0.73
     empath
    -0.70
    áµ
    -0.69
     pronoun
    -0.69
     msec
    -0.68
     texted
    -0.65
     expresses
    -0.65
     dressing
    -0.63
     cues
    -0.63
    POSITIVE LOGITS
     IPO
    0.99
     bankrupt
    0.98
     defunct
    0.96
     privat
    0.91
     bankruptcy
    0.90
     profitable
    0.86
     merger
    0.86
     fledgling
    0.82
     lucrative
    0.82
     privatization
    0.82
    Activations Density 0.719%

    No Known Activations