INDEX

Explanations

mentions of specific locations, with a focus on New York City

oai_token-act-pair · gpt-3.5-turbo

occurrences of the preposition "in."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 convol

-0.75

ername

-0.69

FTWARE

-0.62

 needles

-0.60

 racket

-0.59

rious

-0.58

 infer

-0.58

weather

-0.58

 ingred

-0.58

 spoil

-0.58

POSITIVE LOGITS

 particular

1.43

 nutshell

1.13

verts

1.10

ked

1.06

vert

0.98

version

0.95

 fact

0.92

clusions

0.89

bound

0.89

pires

0.87

Activations Density 0.265%

mentions of specific locations, with a focus on New York City

occurrences of the preposition "in."

No Comments

No Known Activations