INDEX

Explanations

trigger phrases like "Every" followed by a noun, likely referring to recurring events or statements

oai_token-act-pair · gpt-3.5-turbo

the word "Every" indicating frequency or repetition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 Metatron

-0.65

dict

-0.63

olas

-0.62

Viz

-0.62

Ü

-0.61

ainment

-0.61

que

-0.59

Osw

-0.58

rovers

-0.57

he

-0.56

POSITIVE LOGITS

THING

1.41

where

1.15

body

1.01

WHERE

0.97

 conceivable

0.94

ursday

0.88

things

0.85

single

0.85

day

0.84

ĸļ

0.82

Activations Density 0.037%

trigger phrases like "Every" followed by a noun, likely referring to recurring events or statements

the word "Every" indicating frequency or repetition

No Comments

No Known Activations