Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 15494
    Prev
    Next
    INDEX
    Explanations

    phrases describing the quality or nature of things

    oai_token-act-pair · gpt-3.5-turbo

    expressions of quality and importance

    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
    MAP
    -0.79
    idav
    -0.70
    Shut
    -0.69
    pes
    -0.68
    SpaceEngineers
    -0.61
    plets
    -0.59
     Walls
    -0.57
    Downloadha
    -0.57
    adan
    -0.57
    ansas
    -0.56
    POSITIVE LOGITS
     magnitude
    1.38
     caliber
    1.19
     importance
    1.15
     il
    1.14
     stature
    1.14
     nature
    1.13
     calib
    1.10
     origin
    1.09
     proportions
    1.04
     sorts
    1.01
    Activations Density 0.282%

    No Known Activations