INDEX

Explanations

phrases related to actions involving changing, toggling, or shifting between different options or states

oai_token-act-pair · gpt-3.5-turbo

terms related to the concept of "switching" or changing states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

za

-0.77

apolis

-0.65

ICAN

-0.63

icist

-0.63

zza

-0.63

ALE

-0.63

ORED

-0.62

raham

-0.62

Chicken

-0.61

ORE

-0.61

POSITIVE LOGITS

grass

0.97

 switch

0.95

blade

0.94

switch

0.89

 switches

0.85

aroo

0.84

backs

0.84

gear

0.84

 switched

0.78

 switching

0.78

Activations Density 0.020%

phrases related to actions involving changing, toggling, or shifting between different options or states

terms related to the concept of "switching" or changing states

No Comments

No Known Activations