INDEX

Explanations

words or phrases related to specific names or titles

oai_token-act-pair · gpt-3.5-turbo

the repeated mention of a particular linguistic particle or character

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 reflex

-0.79

 metic

-0.76

 favor

-0.75

 grazing

-0.74

 spir

-0.73

 clitor

-0.72

 favour

-0.72

 scram

-0.71

 clipping

-0.70

 saddle

-0.69

POSITIVE LOGITS

ï¸ı

1.26

Because

0.97

ecause

0.90

ï¸

0.90

They

0.89

sure

0.87

Unless

0.87

It

0.86

Sure

0.86

Therefore

0.86

Activations Density 0.137%

words or phrases related to specific names or titles

the repeated mention of a particular linguistic particle or character

No Comments

No Known Activations