INDEX

Explanations

proper nouns specifically related to the name "Lawson" with various activations indicating different levels of relevance

oai_token-act-pair · gpt-3.5-turbo

names of individuals associated with a specific context or event

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

gate

-0.76

 Feet

-0.74

 Turing

-0.71

atted

-0.69

teen

-0.69

 Laden

-0.69

rika

-0.68

lehem

-0.68

Fib

-0.67

Ħ¢

-0.67

POSITIVE LOGITS

amn

0.77

isson

0.76

cean

0.73

 tremend

0.73

rontal

0.72

xual

0.72

illac

0.72

amins

0.70

nington

0.69

emaker

0.68

Activations Density 0.024%

proper nouns specifically related to the name "Lawson" with various activations indicating different levels of relevance

names of individuals associated with a specific context or event

No Comments

No Known Activations