INDEX

Explanations

phrases or sentences that include the word "reason for"

oai_token-act-pair · gpt-3.5-turbo

reasons or justifications for actions or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ros

-0.78

jab

-0.78

tle

-0.74

thumbnails

-0.72

chin

-0.71

arta

-0.71

cks

-0.68

ologies

-0.68

OLOGY

-0.68

heit

-0.68

POSITIVE LOGITS

why

0.98

 inaction

0.92

 preferring

0.85

bidden

0.80

 dismissing

0.78

 commuting

0.77

 hesitation

0.77

laz

0.76

 issuing

0.76

 staying

0.75

Activations Density 0.071%

phrases or sentences that include the word "reason for"

reasons or justifications for actions or events

No Comments

No Known Activations