INDEX

Explanations

mentions of mock scenarios or representations

oai_token-act-pair · gpt-3.5-turbo

references to mockumentaries

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

 Horizon

-0.79

 cryst

-0.78

 FORM

-0.72

 arrang

-0.72

 violet

-0.66

 safegu

-0.63

hips

-0.62

ither

-0.61

 vested

-0.61

è£ħ

-0.60

POSITIVE LOGITS

ument

1.11

eries

0.98

tails

0.93

ups

0.93

ingly

0.90

 Mock

0.89

ery

0.88

atory

0.83

uppet

0.81

crow

0.77

Activations Density 0.033%

mentions of mock scenarios or representations

references to mockumentaries

No Comments

No Known Activations