INDEX

Explanations

phrases related to specific individuals or entities, possibly related to sports or business

oai_token-act-pair · gpt-3.5-turbo

words related to various forms of "doing" or "performing."

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

Neg

-0.76

 Leilan

-0.75

ublic

-0.72

reon

-0.69

hemat

-0.69

________________________________________________________________

-0.67

ensable

-0.67

Weather

-0.66

Altern

-0.66

WD

-0.64

POSITIVE LOGITS

ning

1.00

HAM

0.95

ham

0.84

stocks

0.81

brook

0.79

bach

0.78

ding

0.77

theless

0.77

ned

0.76

alties

0.75

Activations Density 0.013%

phrases related to specific individuals or entities, possibly related to sports or business

words related to various forms of "doing" or "performing."

No Comments

No Known Activations