INDEX

Explanations

phrases indicating a conclusion or final thought

oai_token-act-pair · gpt-3.5-turbo

conclusive statements or summaries at the end of paragraphs

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

mong

-0.66

dec

-0.62

ocl

-0.60

ga

-0.58

ung

-0.57

lis

-0.57

folk

-0.56

lands

-0.56

anim

-0.56

umerable

-0.56

POSITIVE LOGITS

icia

0.84

 reunited

0.78

hiba

0.72

icates

0.69

elvet

0.69

oner

0.67

CoC

0.65

aire

0.65

icating

0.64

 conclud

0.64

Activations Density 0.021%

phrases indicating a conclusion or final thought

conclusive statements or summaries at the end of paragraphs

No Comments

No Known Activations