INDEX

Explanations

references to sequels

oai_token-act-pair · gpt-3.5-turbo

mentions of sequels 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 @ 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

hoff

-0.65

WI

-0.61

govtrack

-0.61

ractor

-0.60

·

-0.60

 Hockey

-0.60

las

-0.59

Ĭ±

-0.59

athering

-0.58

 Organization

-0.58

POSITIVE LOGITS

 sequel

1.12

 sequels

1.03

ngth

0.84

arily

0.80

 thereto

0.79

 conclud

0.78

quit

0.77

 playthrough

0.74

arium

0.74

isSpecialOrderable

0.74

Activations Density 0.010%

references to sequels

mentions of sequels in various contexts

No Comments

No Known Activations