INDEX

Explanations

phrases related to dependency or reliance

oai_token-act-pair · gpt-3.5-turbo

instances of the word "dependent" and its variations

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

ific

-0.77

spir

-0.75

iverpool

-0.74

efer

-0.73

uber

-0.72

mberg

-0.71

éŃĶ

-0.71

shr

-0.70

VERTIS

-0.69

tell

-0.68

POSITIVE LOGITS

 reliant

0.89

 dependent

0.89

 adolesc

0.89

 dependency

0.81

encies

0.78

doms

0.77

 cripp

0.75

 clauses

0.75

 upon

0.75

 citiz

0.74

Activations Density 0.010%

phrases related to dependency or reliance

instances of the word "dependent" and its variations

No Comments

No Known Activations