© 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. 10-RES-JB
    11. 12826
    Prev
    Next
    INDEX
    Explanations

    names starting with "Er" followed by a single letter evenly between 8 and 10

    oai_token-act-pair · gpt-3.5-turbo

    the name "Er" followed by various related contexts or phrases

    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
    esses
    -0.79
    ãģ®éŃĶ
    -0.71
     sight
    -0.63
    rontal
    -0.61
     gulf
    -0.60
     laps
    -0.59
    kefeller
    -0.59
     AMERICA
    -0.59
    ombat
    -0.58
    essed
    -0.57
    POSITIVE LOGITS
    bil
    1.32
    rors
    1.23
    asure
    1.21
    aser
    1.16
    lang
    1.14
    asm
    1.08
    lich
    0.99
    win
    0.98
    asing
    0.98
    mine
    0.98
    Activations Density 0.016%

    No Known Activations