INDEX

Explanations

phrases indicating a hypothetical situation with an element of comparison or speculation

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

aires

-0.68

idates

-0.64

 moderation

-0.62

 Regions

-0.60

vine

-0.59

 Liberal

-0.59

 cited

-0.58

 Globe

-0.58

 Cultural

-0.58

 Progressive

-0.57

POSITIVE LOGITS

 magically

0.77

icket

0.73

pi

0.73

rael

0.72

 somehow

0.72

 rehears

0.69

rir

0.68

 conflic

0.68

Ãł

0.68

 superhuman

0.68

Activations Density 0.222%

phrases indicating a hypothetical situation with an element of comparison or speculation

No Comments

No Known Activations