INDEX

Explanations

actions or events that are reactions, responses, extensions, affirmations, reflections, commentaries, relics, or updates

oai_token-act-pair · gpt-3.5-turbo

terms related to reactions and responses to events or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Cups

-0.83

vironments

-0.77

rooms

-0.70

 Dates

-0.67

 Empires

-0.67

azes

-0.66

pages

-0.65

 Wheels

-0.65

 transitions

-0.65

ovies

-0.64

POSITIVE LOGITS

 reminder

0.96

 unto

0.81

iment

0.79

 akin

0.79

 testament

0.76

 aimed

0.74

 reflection

0.74

isal

0.74

 attempt

0.71

 thereof

0.71

Activations Density 0.248%

actions or events that are reactions, responses, extensions, affirmations, reflections, commentaries, relics, or updates

terms related to reactions and responses to events or conditions

No Comments

No Known Activations