© 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. 2028
    Prev
    Next
    INDEX
    Explanations

    phrases related to arrival or reaching a destination

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the word "came."

    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
    olor
    -0.88
    ²¾
    -0.87
    raid
    -0.87
    illusion
    -0.85
    heed
    -0.81
    inguished
    -0.77
    lav
    -0.76
    apixel
    -0.76
    icon
    -0.75
    orthodox
    -0.75
    POSITIVE LOGITS
     undone
    1.08
     WRITE
    0.84
     ashore
    0.84
     out
    0.80
     pouring
    0.75
     forth
    0.74
     Lans
    0.72
     OUT
    0.71
     up
    0.71
     forward
    0.71
    Activations Density 0.048%

    No Known Activations