INDEX

Explanations

phrases related to a specific person or name "Cahill"

oai_token-act-pair · gpt-3.5-turbo

the names and references of specific individuals and organizations

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

osph

-0.89

angel

-0.77

ulo

-0.76

otent

-0.76

ugal

-0.75

 nomine

-0.74

wart

-0.72

arious

-0.71

htaking

-0.70

etheless

-0.69

POSITIVE LOGITS

bucks

0.87

agate

0.77

RED

0.70

 Hyder

0.67

 Rwanda

0.67

 Connection

0.65

Rao

0.65

rera

0.65

 Waterloo

0.65

 Connect

0.64

Activations Density 0.044%

phrases related to a specific person or name "Cahill"

the names and references of specific individuals and organizations

No Comments

No Known Activations