INDEX

Explanations

terms related to adjustments or balance in various contexts

oai_token-act-pair · gpt-3.5-turbo

attributes related to adjustments, balance, and emotional states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 signature

-0.82

 wire

-0.77

 countdown

-0.75

 mushrooms

-0.73

 chant

-0.71

nap

-0.71

 grav

-0.71

lav

-0.70

eters

-0.69

 reign

-0.68

POSITIVE LOGITS

adjusted

2.86

rounded

2.46

balanced

2.09

broken

2.04

meaning

1.66

average

1.29

intention

1.26

edited

1.26

biased

1.22

balance

1.20

Activations Density 0.039%

terms related to adjustments or balance in various contexts

attributes related to adjustments, balance, and emotional states

No Comments

No Known Activations