INDEX

Explanations

phrases related to observing or analyzing information

oai_token-act-pair · gpt-3.5-turbo

variations of the word "look" and its different forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

eer

-0.62

 delinqu

-0.60

theless

-0.59

mint

-0.59

 Toys

-0.58

icipated

-0.57

ilts

-0.55

cape

-0.55

 Grac

-0.54

Own

-0.53

POSITIVE LOGITS

ression

0.91

 squarely

0.84

 deeper

0.84

at

0.83

 specifically

0.78

 closely

0.77

 into

0.77

 ahead

0.76

 retrospect

0.75

 Ahead

0.75

Activations Density 0.050%

phrases related to observing or analyzing information

variations of the word "look" and its different forms

No Comments

No Known Activations