INDEX

Explanations

phrases related to behind-the-scenes activities

oai_token-act-pair · gpt-3.5-turbo

references to behind-the-scenes activities or events

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

RIC

-0.75

arily

-0.70

ERG

-0.63

fy

-0.60

nu

-0.60

dylib

-0.58

tm

-0.58

 fined

-0.57

luster

-0.57

lance

-0.57

POSITIVE LOGITS

 scenes

1.22

 curtain

1.08

 Scenes

1.01

 curtains

0.84

 veil

0.80

scenes

0.79

 wheel

0.73

 curve

0.73

 desk

0.71

 scene

0.69

Activations Density 0.087%

phrases related to behind-the-scenes activities

references to behind-the-scenes activities or events

No Comments

No Known Activations