INDEX

Explanations

mentions of or references to small or miniature objects or entities

oai_token-act-pair · gpt-3.5-turbo

references to small or diminutive items or concepts, particularly related to the word "itty."

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

xual

-0.87

ppelin

-0.85

isco

-0.80

oway

-0.79

omen

-0.77

ovie

-0.74

ese

-0.74

ications

-0.73

indal

-0.73

orescence

-0.73

POSITIVE LOGITS

abyte

0.82

bilt

0.81

 litter

0.81

 tract

0.79

abytes

0.78

ãĤ¡

0.72

Pry

0.72

 gritty

0.71

gets

0.70

ãĤ´

0.68

Activations Density 0.032%

mentions of or references to small or miniature objects or entities

references to small or diminutive items or concepts, particularly related to the word "itty."

No Comments

No Known Activations