© 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. 2-RES-JB
    11. 8373
    Prev
    Next
    INDEX
    Explanations

    names of specific locations

    oai_token-act-pair · gpt-3.5-turbo

    geographical locations and notable names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Citiz
    -0.65
    etheless
    -0.63
    Downloadha
    -0.62
     youthful
    -0.60
     constitu
    -0.56
    opausal
    -0.54
    ettel
    -0.53
    PUT
    -0.52
    upon
    -0.52
     subsistence
    -0.52
    POSITIVE LOGITS
     Productions
    0.61
    !--
    0.59
    rack
    0.56
     Butt
    0.54
    isan
    0.52
    cliffe
    0.52
    ĸļ
    0.52
     Robot
    0.52
    ys
    0.51
     Racer
    0.51
    Activations Density 2.111%

    No Known Activations