INDEX

Explanations

specific items from a list

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "list" 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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Aber

-0.64

 sailing

-0.60

lat

-0.60

 pounding

-0.60

 stride

-0.59

McD

-0.59

 leisure

-0.57

 beat

-0.57

 satur

-0.57

 whist

-0.56

POSITIVE LOGITS

ening

1.09

eners

1.04

erv

0.98

ener

0.95

list

0.92

erness

0.91

ing

0.86

erve

0.84

hoff

0.84

witz

0.83

Activations Density 0.014%

specific items from a list

occurrences of the word "list" in various contexts

No Comments

No Known Activations