INDEX

Explanations

references to specific locations or directions

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

acca

-0.78

manship

-0.75

utm

-0.73

successfully

-0.72

uates

-0.72

thood

-0.71

teness

-0.70

oppable

-0.70

bourg

-0.70

pers

-0.69

POSITIVE LOGITS

 bathroom

1.22

 attic

1.17

 kitchen

1.16

 nearest

1.14

 restroom

1.10

 toilet

1.08

 fireplace

1.06

 fridge

1.04

 coolest

1.04

 beach

1.01

Activations Density 0.354%

references to specific locations or directions

occurrences of the word "the."

No Comments

No Known Activations