INDEX

Explanations

references to the city "Delhi."

oai_token-act-pair · gpt-3.5-turbo

references to locations or names associated with "Delhi."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

PsyNetMessage

-0.96

 Asylum

-0.85

osate

-0.71

abc

-0.68

nton

-0.67

toggle

-0.66

wick

-0.66

 Merrill

-0.65

ndum

-0.64

 Paige

-0.64

POSITIVE LOGITS

aware

1.02

uxe

0.96

usional

0.93

DEL

0.88

aneously

0.85

indal

0.82

ivery

0.81

aughter

0.79

 Pradesh

0.79

icate

0.78

Activations Density 0.005%

references to the city "Delhi."

references to locations or names associated with "Delhi."

No Comments

No Known Activations