© 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. 20484
    Prev
    Next
    INDEX
    Explanations

    mentions related to magnification, enhancement, or importance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Magn" and its variations

    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
    TING
    -0.74
    OPLE
    -0.70
    INESS
    -0.68
    lde
    -0.66
    ting
    -0.65
     solicitation
    -0.63
    fters
    -0.63
    ERG
    -0.62
    starter
    -0.62
    ħĭ
    -0.62
    POSITIVE LOGITS
    olia
    1.50
    ificant
    1.44
    ificent
    1.40
    animous
    1.39
    ific
    1.22
    itudes
    1.22
    anim
    1.07
    itude
    1.02
    ifying
    1.02
    ified
    0.98
    Activations Density 0.033%

    No Known Activations