INDEX

Explanations

introverted descriptions or characteristics

oai_token-act-pair · gpt-3.5-turbo

terms related to introversion and introspective qualities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Millennium

-0.79

RY

-0.68

 Ivory

-0.64

 Sons

-0.62

 Sutherland

-0.62

 Laurent

-0.58

 Pharmaceutical

-0.58

 Shelley

-0.58

 Liang

-0.57

 Parm

-0.57

POSITIVE LOGITS

spection

1.76

spective

1.58

verted

1.48

vert

1.18

spect

1.18

verts

1.13

version

1.00

itial

0.95

verting

0.93

jection

0.92

Activations Density 0.015%

introverted descriptions or characteristics

terms related to introversion and introspective qualities

No Comments

No Known Activations