INDEX

Explanations

words related to the extent or boundaries of a concept or issue

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "scope" 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 @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

maid

-0.69

\":

-0.67

Pass

-0.66

 Valentine

-0.66

ston

-0.65

Indust

-0.63

joining

-0.62

Beat

-0.61

 pengu

-0.61

Mart

-0.60

POSITIVE LOGITS

 scope

1.21

 Scope

1.05

illary

0.86

scope

0.83

Scope

0.82

ategory

0.78

mares

0.78

psons

0.77

emouth

0.76

opes

0.75

Activations Density 0.010%

words related to the extent or boundaries of a concept or issue

references to the concept of "scope" in various contexts

No Comments

No Known Activations