INDEX

Explanations

words related to days of the week

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter 's' 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Marginal

-0.61

 hypert

-0.60

 Leilan

-0.59

 subcontract

-0.59

esp

-0.58

ļéĨĴ

-0.57

mass

-0.56

 restrained

-0.56

estern

-0.56

EStream

-0.55

POSITIVE LOGITS

terday

1.04

outheast

0.83

borough

0.82

ales

0.81

ween

0.81

arnaev

0.80

peed

0.79

herry

0.78

ername

0.76

forth

0.75

Activations Density 0.123%

words related to days of the week

occurrences of the letter 's' in various contexts

No Comments

No Known Activations