INDEX

Explanations

action words or verbs preceded by specific keywords

oai_token-act-pair · gpt-3.5-turbo

words and phrases indicating evaluations or comparisons

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

Operation

-0.88

pmwiki

-0.86

WER

-0.86

Leaks

-0.79

NCT

-0.79

FontSize

-0.74

Wiki

-0.72

edIn

-0.70

Secondly

-0.68

Prosecut

-0.67

POSITIVE LOGITS

llo

0.83

acon

0.78

 underscore

0.71

atos

0.70

ck

0.67

stem

0.67

pload

0.66

cients

0.65

cin

0.65

adv

0.64

Activations Density 0.455%

action words or verbs preceded by specific keywords

words and phrases indicating evaluations or comparisons

No Comments

No Known Activations