INDEX

Explanations

adjectives related to emotional states

oai_token-act-pair · gpt-3.5-turbo

expressions of strong emotional states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Downloadha

-0.86

ilege

-0.79

orthy

-0.74

lished

-0.73

 distingu

-0.73

cellence

-0.72

limited

-0.71

Jump

-0.71

Ranked

-0.70

interstitial

-0.69

POSITIVE LOGITS

 onlook

1.35

 bystanders

1.09

 spectators

1.04

 parents

1.03

 populace

1.03

 crowds

1.02

 locals

1.01

 villagers

1.01

 glances

0.98

 eyes

0.97

Activations Density 0.168%

adjectives related to emotional states

expressions of strong emotional states

No Comments

No Known Activations