© 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. 8901
    Prev
    Next
    INDEX
    Explanations

    phrases related to highlighting or pointing out specific information

    oai_token-act-pair · gpt-3.5-turbo

    references to indicators or signs of various conditions or events

    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
    ILLE
    -0.76
     hyster
    -0.67
    æ©Ł
    -0.66
    OTE
    -0.64
    ettel
    -0.60
    ECD
    -0.60
    ADS
    -0.59
    erest
    -0.58
     tides
    -0.58
     GEAR
    -0.58
    POSITIVE LOGITS
    manship
    1.39
    marks
    1.04
    emark
    0.91
     marks
    0.86
    mark
    0.86
    pelled
    0.86
    mas
    0.84
    terday
    0.84
    eting
    0.82
    ovi
    0.81
    Activations Density 0.012%

    No Known Activations