INDEX

Explanations

words related to potentially negative situations or outcomes

oai_token-act-pair · gpt-3.5-turbo

words indicating potential outcomes or risks

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

baugh

-0.85

bern

-0.76

ger

-0.76

core

-0.75

fare

-0.71

vation

-0.71

woods

-0.70

ablishment

-0.69

otle

-0.69

ĸļ

-0.69

POSITIVE LOGITS

 jeopard

0.96

 hazardous

0.95

 lethal

0.86

 synerg

0.84

 contam

0.82

 habitable

0.81

 damaging

0.79

 harmful

0.79

 disrupt

0.78

 dangerous

0.77

Activations Density 0.028%

words related to potentially negative situations or outcomes

words indicating potential outcomes or risks

No Comments

No Known Activations