INDEX

Explanations

terms related to customizations and generalizations

oai_token-act-pair · gpt-3.5-turbo

words related to various types of "izations" or "ations."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 element

-0.63

oret

-0.61

 mechanism

-0.60

noon

-0.59

 corridor

-0.58

 magnet

-0.58

 scra

-0.58

 embryo

-0.57

 Effect

-0.57

 cake

-0.56

POSITIVE LOGITS

izations

2.31

isations

2.13

ulations

2.02

utions

1.79

urations

1.77

ieties

1.75

usions

1.74

asions

1.74

agements

1.73

iances

1.73

Activations Density 0.060%

terms related to customizations and generalizations

words related to various types of "izations" or "ations."

No Comments

No Known Activations