INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

the word "had" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

bie

-0.66

âĻ¦

-0.65

bery

-0.65

orph

-0.64

PI

-0.64

alias

-0.64

coin

-0.62

owe

-0.61

forward

-0.60

hack

-0.60

POSITIVE LOGITS

 been

1.11

 undergone

1.03

iths

1.01

 begun

0.97

 gotten

0.91

 previously

0.91

 gone

0.91

 originally

0.90

 hoped

0.87

 flown

0.79

Activations Density 0.156%

proper nouns

the word "had" in various contexts

No Comments

No Known Activations