© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    11. 19264
    Prev
    Next
    INDEX
    Explanations

    phrases related to primers or introductory materials

    oai_token-act-pair · gpt-3.5-turbo

    references to "primer" as a term or concept in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    illes
    -0.69
    earable
    -0.69
    ãģ®é
    -0.68
     Employment
    -0.68
    haw
    -0.67
     SQU
    -0.66
     Bever
    -0.65
    inson
    -0.65
     Aviation
    -0.65
    atz
    -0.65
    POSITIVE LOGITS
     Prim
    3.47
    prim
    2.84
    Prim
    2.75
     prim
    2.53
     primer
    2.01
     primitive
    1.88
     Primal
    1.46
     primed
    1.26
     primal
    1.26
     Primordial
    1.11
    Activations Density 0.040%

    No Known Activations