INDEX

Explanations

phrases related to actions taken or events happening

oai_token-act-pair · gpt-3.5-turbo

pronouns used 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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hap

-0.66

Hok

-0.60

 Seah

-0.58

ophon

-0.57

Tam

-0.54

advertisement

-0.54

 Buddhism

-0.53

ivably

-0.53

___

-0.51

 endif

-0.51

POSITIVE LOGITS

 Seym

0.65

psc

0.64

\",

0.64

enum

0.62

tro

0.62

 streng

0.61

saf

0.60

eded

0.59

merce

0.57

 guiActiveUn

0.56

Activations Density 0.374%

phrases related to actions taken or events happening

pronouns used in various contexts

No Comments

No Known Activations