INDEX

Explanations

statements indicating fairness, similarity, or comparison

oai_token-act-pair · gpt-3.5-turbo

the word "equally" and its various usages throughout the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

glers

-0.73

 Coff

-0.73

liest

-0.71

 Canaver

-0.68

ocene

-0.65

 Encyclopedia

-0.63

Fry

-0.62

gest

-0.62

 Landing

-0.62

Buy

-0.61

POSITIVE LOGITS

 spaced

0.97

 weighted

0.90

 situated

0.89

imilar

0.88

 sized

0.87

 adept

0.80

inguishable

0.78

 applicable

0.77

 opposed

0.74

 ruthless

0.72

Activations Density 0.026%

statements indicating fairness, similarity, or comparison

the word "equally" and its various usages throughout the text

No Comments

No Known Activations