INDEX

Explanations

descriptions or discussions related to various types of experiences

oai_token-act-pair · gpt-3.5-turbo

discussions centered around user experiences

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

inately

-0.76

prus

-0.73

roup

-0.70

enforcement

-0.68

nod

-0.68

enta

-0.68

aye

-0.66

cmp

-0.66

yright

-0.66

cott

-0.65

POSITIVE LOGITS

ually

1.03

urable

0.82

ional

0.76

ual

0.75

 immersion

0.73

 Experience

0.72

iliar

0.72

 experiences

0.71

 abroad

0.71

ivity

0.71

Activations Density 0.042%

descriptions or discussions related to various types of experiences

discussions centered around user experiences

No Comments

No Known Activations