INDEX

Explanations

words related to various forms of embodiment or manifestation

oai_token-act-pair · gpt-3.5-turbo

terms related to forms and representations of characters or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

Ô

-0.70

urrent

-0.69

ł

-0.69

fman

-0.69

rib

-0.68

iland

-0.67

ician

-0.66

cott

-0.65

ifty

-0.64

picking

-0.64

POSITIVE LOGITS

 incarnation

1.17

 incarn

1.11

 thereof

0.82

 Incarn

0.77

 Incarnation

0.76

 avatar

0.72

 Archangel

0.72

 reborn

0.71

 iteration

0.71

 embodied

0.71

Activations Density 0.038%

words related to various forms of embodiment or manifestation

terms related to forms and representations of characters or concepts

No Comments

No Known Activations