INDEX

Explanations

phrases related to instructions or tutorials

oai_token-act-pair · gpt-3.5-turbo

sentences that express requests, commands, or specific conditions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

"—

-0.78

 ÂŃ

-0.73

)].

-0.72

)—

-0.71

 kindred

-0.70

—"

-0.70

ocaust

-0.69

AFP

-0.69

.–

-0.68

foundland

-0.68

POSITIVE LOGITS

oret

0.66

sequently

0.66

Previously

0.66

Specifically

0.66

 latter

0.65

 furthermore

0.65

 Leilan

0.64

Basically

0.64

itialized

0.63

itionally

0.63

Activations Density 0.716%

phrases related to instructions or tutorials

sentences that express requests, commands, or specific conditions

No Comments

No Known Activations