INDEX

Explanations

numerical approximations or estimates

oai_token-act-pair · gpt-3.5-turbo

words related to estimated quantities or approximations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

LINE

-0.78

rums

-0.76

stru

-0.73

gae

-0.72

Reviewer

-0.70

starter

-0.67

keeper

-0.67

hook

-0.66

Files

-0.66

culosis

-0.64

POSITIVE LOGITS

imates

1.35

imate

1.32

imating

1.16

imated

1.04

 approximate

0.95

imation

0.94

 approx

0.90

rox

0.88

oby

0.83

urations

0.80

Activations Density 0.007%

numerical approximations or estimates

words related to estimated quantities or approximations

No Comments

No Known Activations