INDEX

Explanations

adjectives related to severity or intensity

oai_token-act-pair · gpt-3.5-turbo

references to severe or tough 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

ovember

-0.92

phis

-0.91

ITNESS

-0.82

cellent

-0.81

ĸļ

-0.78

assies

-0.75

ublic

-0.75

ICLE

-0.75

ividual

-0.72

agine

-0.72

POSITIVE LOGITS

 harsh

1.03

ness

0.93

 harshly

0.92

 retribution

0.88

 punishments

0.88

 winters

0.86

nesses

0.85

 harsher

0.85

 punitive

0.84

ened

0.84

Activations Density 0.025%

adjectives related to severity or intensity

references to severe or tough situations

No Comments

No Known Activations