INDEX

Explanations

instances of the word "bit" within various contexts

oai_token-act-pair · gpt-3.5-turbo

references to incremental or gradual changes

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

ammad

-0.76

etheus

-0.71

 pend

-0.67

theless

-0.64

velt

-0.64

 Pend

-0.64

Vaj

-0.64

gaard

-0.63

anguage

-0.63

 Duty

-0.62

POSITIVE LOGITS

terness

1.25

umen

1.13

ches

1.12

buck

1.02

ching

1.00

wig

0.99

umin

0.97

chery

0.97

ters

0.91

meal

0.91

Activations Density 0.026%

instances of the word "bit" within various contexts

references to incremental or gradual changes

No Comments

No Known Activations