© 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. 3-RES-JB
    11. 6893
    Prev
    Next
    INDEX
    Explanations

    references to the character "Elmo"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "mo" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ICLE
    -0.67
     AAP
    -0.67
    Interstitial
    -0.66
     caution
    -0.65
    AMS
    -0.65
     ire
    -0.65
     Identification
    -0.64
     UID
    -0.62
     halls
    -0.61
     Integrity
    -0.59
    POSITIVE LOGITS
    ogle
    1.01
    edia
    1.00
    zilla
    1.00
    obic
    0.99
    ose
    0.96
    ovies
    0.92
    obil
    0.92
    astic
    0.91
    ooth
    0.90
    aned
    0.89
    Activations Density 0.007%

    No Known Activations