INDEX

Explanations

the word "so" followed by a verb or action

oai_token-act-pair · gpt-3.5-turbo

the word "so" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 glances

-0.59

 muse

-0.59

Wer

-0.57

theless

-0.57

 cradle

-0.56

 realities

-0.56

ãģ£

-0.56

 grunt

-0.55

 denial

-0.54

sein

-0.54

POSITIVE LOGITS

bered

1.19

othes

1.15

apy

1.03

oths

0.99

oner

0.97

othe

0.97

oooo

0.88

aps

0.88

ooo

0.84

far

0.83

Activations Density 0.076%

the word "so" followed by a verb or action

the word "so" in various contexts

No Comments

No Known Activations