© 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. 387
    Prev
    Next
    INDEX
    Explanations

    phrases related to company values and missions

    oai_token-act-pair · gpt-3.5-turbo

    statements related to quality and commitment in various contexts

    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
     rumored
    -0.78
    arro
    -0.75
     fucked
    -0.75
     faint
    -0.74
     dummy
    -0.73
     bombshell
    -0.72
     stash
    -0.72
     Frankenstein
    -0.71
     strang
    -0.71
     gasp
    -0.70
    POSITIVE LOGITS
     strives
    1.06
     ensuring
    1.02
     Integrity
    1.02
     Ens
    0.96
     maximizing
    0.94
     Diversity
    0.93
     fostering
    0.92
     priorit
    0.91
    Quality
    0.91
    cellence
    0.91
    Activations Density 0.881%

    No Known Activations