INDEX

Explanations

words related to introspection or inward reflection

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "intro" and its variations, indicating a focus on introductions or introductory content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Millennium

-0.74

 precincts

-0.68

 Sutherland

-0.66

 Laurent

-0.64

 Ivory

-0.63

 Shogun

-0.63

 Massacre

-0.63

 Franks

-0.62

 precinct

-0.60

 Mechdragon

-0.59

POSITIVE LOGITS

spection

1.90

spective

1.79

verted

1.63

spect

1.40

vert

1.27

verts

1.24

version

1.19

verting

1.09

jection

1.08

hibited

1.06

Activations Density 0.031%

words related to introspection or inward reflection

occurrences of the word "intro" and its variations, indicating a focus on introductions or introductory content

No Comments

No Known Activations

words related to introspection or inward reflection

occurrences of the word "intro" and its variations, indicating a focus on introductions or introductory content

No Comments

No Known Activations