INDEX

Explanations

the word "lead."

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "lead" 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

Negative Logits

ramid

-0.70

Sov

-0.69

ALLY

-0.68

 mercy

-0.67

aves

-0.67

afort

-0.65

pload

-0.64

eatures

-0.63

 Remem

-0.63

BLIC

-0.63

POSITIVE LOGITS

ership

1.09

better

1.01

gers

0.83

wig

0.82

hole

0.80

boards

0.80

 negotiator

0.72

 bearer

0.71

erer

0.69

 nurturing

0.68

Activations Density 0.038%

the word "lead."

occurrences of the word "lead" in various contexts

No Known Activations