INDEX

Explanations

words related to the extent or boundaries of something

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 @ 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

maid

-0.71

 Valentine

-0.67

 pengu

-0.66

ston

-0.66

ocard

-0.63

ublic

-0.63

eah

-0.60

 dime

-0.59

 Zimmer

-0.59

vance

-0.58

POSITIVE LOGITS

 scope

1.13

 Scope

0.96

illary

0.82

Scope

0.82

izons

0.77

 creep

0.76

scope

0.73

emouth

0.72

cale

0.71

xes

0.71

Activations Density 0.015%

words related to the extent or boundaries of something

references to the concept of "scope" in various contexts

No Comments

No Known Activations