INDEX

Explanations

mentions of the word "So" followed by other words

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "So" and its variations

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

theless

-0.59

 reel

-0.59

 juggling

-0.59

 upside

-0.57

 sequ

-0.56

 recomm

-0.56

 land

-0.55

 ensemble

-0.55

 reclaimed

-0.55

 unequ

-0.54

POSITIVE LOGITS

apy

1.24

oths

1.20

fter

1.15

aked

1.15

vere

1.15

opers

1.14

aring

1.11

bered

1.10

iled

1.10

oner

1.08

Activations Density 0.036%

mentions of the word "So" followed by other words

occurrences of the word "So" and its variations

No Comments

No Known Activations