INDEX

Explanations

comparisons or similarities between different subjects

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "too," indicating a sense of addition or emphasis in statements

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

 caster

-0.70

 Versus

-0.69

 newsp

-0.60

 ONLY

-0.58

elf

-0.58

 technician

-0.56

 Accountability

-0.56

 millisec

-0.56

 mindset

-0.54

earth

-0.54

POSITIVE LOGITS

vous

0.83

 sidx

0.74

Ì¶

0.72

otton

0.72

esson

0.71

ettings

0.71

uld

0.70

LET

0.70

ilon

0.69

endiary

0.68

Activations Density 0.098%

comparisons or similarities between different subjects

instances of the phrase "too," indicating a sense of addition or emphasis in statements

No Comments

No Known Activations