INDEX

Explanations

ways to express two opposing options or perspectives

oai_token-act-pair · gpt-3.5-turbo

phrases involving the concept of "way" in the context of methods or approaches to situations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ishable

-0.80

ĸļ

-0.74

rake

-0.74

usters

-0.72

owship

-0.72

anmar

-0.70

 Cain

-0.70

anse

-0.66

uci

-0.66

uster

-0.65

POSITIVE LOGITS

point

0.95

finding

0.89

fare

0.84

sey

0.76

points

0.73

forward

0.72

PASS

0.71

sided

0.71

frame

0.69

 Mania

0.68

Activations Density 0.030%

ways to express two opposing options or perspectives

phrases involving the concept of "way" in the context of methods or approaches to situations

No Comments

No Known Activations