INDEX

Explanations

mentions of historical battles

oai_token-act-pair · gpt-3.5-turbo

references to historical battles

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

quartered

-0.70

 attribut

-0.65

lessly

-0.64

zsche

-0.63

 precise

-0.63

 derog

-0.63

 coating

-0.62

 dwelling

-0.62

 wrapper

-0.61

qus

-0.61

POSITIVE LOGITS

 Champions

0.91

 sorts

0.84

 course

0.84

 Nanto

0.79

Course

0.74

course

0.72

 Roses

0.71

antz

0.70

 Seasons

0.69

 scrimmage

0.68

Activations Density 0.195%

mentions of historical battles

references to historical battles

No Comments

No Known Activations