INDEX

Explanations

references to martyrdom and related concepts

oai_token-act-pair · gpt-3.5-turbo

references to martyrdom and related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

DragonMagazine

-0.77

PLA

-0.77

 Associates

-0.75

 Nest

-0.72

FN

-0.67

 Akin

-0.67

 Franch

-0.67

 Lines

-0.66

enhagen

-0.64

UG

-0.63

POSITIVE LOGITS

dom

0.84

ted

0.82

milo

0.82

thood

0.81

iour

0.80

yrs

0.79

tle

0.78

eous

0.77

 toast

0.76

ome

0.75

Activations Density 0.028%

references to martyrdom and related concepts

references to martyrdom and related concepts

No Comments

No Known Activations