INDEX

Explanations

short phrases starting with "Part of" followed by a description

oai_token-act-pair · gpt-3.5-turbo

the phrase "part of" followed by various nouns and concepts

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

 butcher

-0.70

 slightest

-0.66

cyt

-0.65

reys

-0.64

Champ

-0.63

dayName

-0.62

ENCE

-0.62

gins

-0.61

 spiders

-0.61

 DRAG

-0.60

POSITIVE LOGITS

assing

0.65

 Armored

0.64

 Hess

0.62

 Kessler

0.61

thouse

0.61

milo

0.61

assed

0.61

scription

0.60

GDP

0.60

 Shutdown

0.59

Activations Density 0.087%

short phrases starting with "Part of" followed by a description

the phrase "part of" followed by various nouns and concepts

No Comments

No Known Activations