INDEX

Explanations

pronouns followed by an action or a statement

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "It."

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

 ILCS

-0.78

Priv

-0.62

idious

-0.61

 Spending

-0.60

 dstg

-0.59

 aversion

-0.59

hips

-0.59

pring

-0.58

å½

-0.58

 Resistance

-0.57

POSITIVE LOGITS

 includes

1.28

's

1.23

'll

1.22

 contains

1.18

 involves

1.18

 reads

1.18

 consists

1.17

 revolves

1.13

 sounds

1.12

 spans

1.11

Activations Density 0.203%

pronouns followed by an action or a statement

occurrences of the word "It."

No Comments

No Known Activations