INDEX

Explanations

phrases related to failure or loss

oai_token-act-pair · gpt-3.5-turbo

references to the concept of defeat

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

 liner

-0.87

atern

-0.74

 pores

-0.73

olen

-0.70

azer

-0.64

OPER

-0.64

acca

-0.63

negie

-0.63

ORPG

-0.62

overe

-0.62

POSITIVE LOGITS

 defeat

1.08

 defeats

1.01

pport

0.87

ptives

0.84

nces

0.82

lessly

0.81

 Defeat

0.80

enance

0.76

ingly

0.74

ery

0.72

Activations Density 0.013%

phrases related to failure or loss

references to the concept of defeat

No Comments

No Known Activations