© 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. 0-RES-JB
    11. 22267
    Prev
    Next
    INDEX
    Explanations

    phrases related to items that are considered disposable

    oai_token-act-pair · gpt-3.5-turbo

    terms related to disposability and low value of entities or objects

    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
     Maze
    -0.76
     Mant
    -0.74
    jong
    -0.73
     Archdemon
    -0.72
    mit
    -0.70
    tun
    -0.70
     Sebast
    -0.70
    oft
    -0.69
    jam
    -0.69
     Lenn
    -0.68
    POSITIVE LOGITS
     disposable
    3.55
     expend
    1.51
     reusable
    1.47
     cardboard
    1.37
     freel
    1.24
     interchangeable
    1.19
     friction
    1.16
     filler
    1.11
     gre
    1.09
     discarded
    1.06
    Activations Density 0.055%

    No Known Activations