INDEX

Explanations

adjectives related to impact or importance

oai_token-act-pair · gpt-3.5-turbo

descriptive adjectives indicating significant or noteworthy features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

ãĤ±

-0.71

ruary

-0.70

uilding

-0.70

ternity

-0.68

ioxide

-0.68

agine

-0.68

aval

-0.68

ravel

-0.66

ordon

-0.65

ategory

-0.64

POSITIVE LOGITS

 aspect

1.48

 thing

1.37

 aspects

1.17

 part

1.16

 feature

1.16

 pecul

1.09

 element

1.06

 takeaway

1.03

 characteristic

1.00

 facet

1.00

Activations Density 0.141%

adjectives related to impact or importance

descriptive adjectives indicating significant or noteworthy features

No Comments

No Known Activations