INDEX

Explanations

comparisons between different entities or concepts

oai_token-act-pair · gpt-3.5-turbo

comparative phrases that express a lack of depth or effectiveness

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

ICA

-0.64

DIT

-0.64

 COUR

-0.64

 Unlock

-0.63

\<

-0.63

 ACTIONS

-0.61

YES

-0.61

WAYS

-0.60

ISM

-0.57

+++

-0.57

POSITIVE LOGITS

imilar

0.91

far

0.88

pired

0.83

 advertised

0.81

 much

0.81

 well

0.79

 flashy

0.79

yet

0.79

leep

0.78

 noticeable

0.78

Activations Density 0.048%

comparisons between different entities or concepts

comparative phrases that express a lack of depth or effectiveness

No Comments

No Known Activations