INDEX

Explanations

words related to mortality or endings

oai_token-act-pair · gpt-3.5-turbo

terms related to death and mortality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

BOOK

-0.64

 Wheeler

-0.64

 Carbuncle

-0.61

 prescribed

-0.61

 peeled

-0.60

 Shining

-0.59

Book

-0.58

 deducted

-0.58

ECH

-0.57

initely

-0.56

POSITIVE LOGITS

gue

1.06

aceutical

0.92

gage

0.90

iday

0.87

cade

0.84

mpeg

0.82

umn

0.82

utes

0.80

idian

0.79

atin

0.79

Activations Density 0.031%

words related to mortality or endings

terms related to death and mortality

No Comments

No Known Activations