INDEX

Explanations

words related to mortality and lethal events

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "death."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Avg

-0.77

Available

-0.75

æ©Ł

-0.74

Cola

-0.73

arity

-0.73

Export

-0.72

ĸļ

-0.71

Ĭ±

-0.70

 Monthly

-0.69

Alpha

-0.69

POSITIVE LOGITS

blow

0.94

stroke

0.87

bed

0.85

lier

0.85

guards

0.84

claw

0.84

touch

0.83

 toll

0.82

mur

0.82

match

0.81

Activations Density 0.027%

words related to mortality and lethal events

occurrences of the word "death."

No Comments

No Known Activations