INDEX

Explanations

adjectives or verbs related to observations or opinions about individuals or groups

oai_token-act-pair · gpt-3.5-turbo

instances of the word "seem" and its variations, indicating uncertainty or perception

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

 Scrib

-0.77

aturdays

-0.66

 Print

-0.65

 Crossing

-0.62

 Grape

-0.62

=-=-=-=-=-=-=-=-

-0.61

ierrez

-0.59

azeera

-0.58

 Combine

-0.58

ierra

-0.58

POSITIVE LOGITS

 oblivious

1.23

 incapable

1.14

 reluctant

1.12

 unaware

1.10

 unwilling

1.09

 poised

1.09

 eager

1.09

 intent

1.08

 unsure

1.07

 unable

1.07

Activations Density 0.066%

adjectives or verbs related to observations or opinions about individuals or groups

instances of the word "seem" and its variations, indicating uncertainty or perception

No Comments

No Known Activations