INDEX

Explanations

phrases mentioning "escape" or derogatory activities

oai_token-act-pair · gpt-3.5-turbo

variations of the word "escrow"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Dynamics

-0.81

Îº

-0.74

 isEnabled

-0.69

KER

-0.67

 Sandy

-0.67

 Eater

-0.66

EEE

-0.65

 Roof

-0.65

 Mother

-0.65

å§«

-0.65

POSITIVE LOGITS

esc

1.22

ript

1.06

ription

1.02

cade

1.00

ribed

0.99

apist

0.96

orts

0.94

ades

0.92

orting

0.89

aded

0.88

Activations Density 0.004%

phrases mentioning "escape" or derogatory activities

variations of the word "escrow"

No Comments

No Known Activations