INDEX

Explanations

the word "there"

oai_token-act-pair · gpt-3.5-turbo

the repeated use of the word "there" 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 @ 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

 Magicka

-0.68

Maw

-0.65

 diarrhea

-0.63

 pound

-0.61

CJ

-0.60

ãĥ¥

-0.57

 cups

-0.57

 Charleston

-0.56

full

-0.56

 franc

-0.55

POSITIVE LOGITS

abouts

1.31

upon

1.05

fore

0.83

otom

0.76

tics

0.75

=\"

0.74

oplan

0.73

FORE

0.72

 fortun

0.71

olkien

0.71

Activations Density 0.084%

the word "there"

the repeated use of the word "there" in various contexts

No Comments

No Known Activations