INDEX

Explanations

introductory phrases or statements, e.g., "First and foremost," "First thing," or "Things first."

oai_token-act-pair · gpt-3.5-turbo

phrases that emphasize the importance of things or ideas

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

interrupted

-0.76

ynt

-0.68

 unfocusedRange

-0.65

 insecure

-0.63

ingen

-0.63

Spoiler

-0.63

abled

-0.63

ulkan

-0.62

ween

-0.61

ancies

-0.61

POSITIVE LOGITS

edly

0.74

 Rouhani

0.72

 Misty

0.72

 foremost

0.72

imester

0.71

 volley

0.70

 introdu

0.66

eve

0.63

 Alexa

0.63

Nev

0.62

Activations Density 0.191%

introductory phrases or statements, e.g., "First and foremost," "First thing," or "Things first."

phrases that emphasize the importance of things or ideas

No Comments

No Known Activations