INDEX

Explanations

instances of the word "wherever"

oai_token-act-pair · gpt-3.5-turbo

various forms of the word "where."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

PHOTOS

-0.66

Riy

-0.64

eers

-0.64

Tex

-0.61

Lob

-0.61

ises

-0.60

 cape

-0.60

oscope

-0.60

ãĥ¼ãĤ¯

-0.60

ki

-0.59

POSITIVE LOGITS

theless

0.91

entimes

0.91

terday

0.90

nown

0.89

leep

0.84

selves

0.83

phalt

0.79

merce

0.79

soever

0.78

 happ

0.78

Activations Density 0.070%

instances of the word "wherever"

various forms of the word "where."

No Comments

No Known Activations