INDEX

Explanations

mentions of the word "Habit" followed by another word or phrase

oai_token-act-pair · gpt-3.5-turbo

the presence of the word "Habit" and titles or names associated with individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

acters

-0.87

othal

-0.77

 Wast

-0.72

 Luxem

-0.70

xtap

-0.65

anwhile

-0.61

lance

-0.60

 stump

-0.59

swer

-0.59

rawdownloadcloneembedreportprint

-0.59

POSITIVE LOGITS

ritz

0.86

ciplinary

0.72

pered

0.72

bay

0.71

daq

0.70

gard

0.69

ja

0.68

ency

0.67

iquette

0.66

fitting

0.66

Activations Density 0.064%

mentions of the word "Habit" followed by another word or phrase

the presence of the word "Habit" and titles or names associated with individuals

No Comments

No Known Activations