INDEX

Explanations

phrases starting with "And."

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "And"

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

manship

-0.68

heads

-0.68

scene

-0.66

atical

-0.65

houses

-0.65

fell

-0.63

cloth

-0.62

=\"

-0.61

ses

-0.61

amer

-0.61

POSITIVE LOGITS

romeda

1.27

rea

1.16

hra

1.15

alus

0.96

 secondly

0.94

rew

0.90

 furthermore

0.88

 then

0.87

rogens

0.86

ersen

0.86

Activations Density 0.088%

phrases starting with "And."

occurrences of the word "And"

No Comments

No Known Activations