INDEX

Explanations

pronouns ('we', 'us', 'our') and verbs related to self-reflection or self-understanding

oai_token-act-pair · gpt-3.5-turbo

references to collective human experiences and interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

market

-0.68

Dash

-0.66

 Saud

-0.63

 Bust

-0.63

 Publication

-0.62

RU

-0.62

FLAG

-0.61

ĳå£«

-0.61

ILA

-0.60

 Rhodes

-0.60

POSITIVE LOGITS

 ourselves

1.14

 unconsciously

1.10

 intu

1.04

 instinctively

1.02

 perceive

1.02

 subconscious

0.93

 mortals

0.89

 gaze

0.89

 humans

0.88

 consume

0.83

Activations Density 0.264%

pronouns ('we', 'us', 'our') and verbs related to self-reflection or self-understanding

references to collective human experiences and interactions

No Comments

No Known Activations