© 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. 1-RES-JB
    11. 24161
    Prev
    Next
    INDEX
    Explanations

    long phrases that start with "Along"

    oai_token-act-pair · gpt-3.5-turbo

    the word "Along" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     insensitive
    -0.75
    usable
    -0.74
    yre
    -0.69
     scr
    -0.67
    istant
    -0.65
    imm
    -0.64
    ptive
    -0.63
     blink
    -0.63
     knock
    -0.61
    aunder
    -0.61
    POSITIVE LOGITS
    along
    0.99
    ward
    0.82
     Along
    0.82
    ãĤ¤ãĥĪ
    0.81
    wagon
    0.81
    ments
    0.79
    side
    0.77
    comings
    0.76
    itialized
    0.76
    ortment
    0.75
    Activations Density 0.007%

    No Known Activations