INDEX

Explanations

proper nouns related to people or organizations

oai_token-act-pair · gpt-3.5-turbo

proper nouns or specific names, particularly those related to individuals and entities in a specific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 conveniently

-0.60

\<

-0.57

lehem

-0.56

SPONSORED

-0.55

 envy

-0.54

 belie

-0.53

 [âĢ¦]

-0.53

 needle

-0.53

EEK

-0.52

 tempo

-0.52

POSITIVE LOGITS

kefeller

1.10

issance

0.97

backer

0.95

hester

0.85

ordan

0.84

earchers

0.82

hani

0.79

zl

0.79

restling

0.78

eway

0.75

Activations Density 0.196%

proper nouns related to people or organizations

proper nouns or specific names, particularly those related to individuals and entities in a specific context

No Comments

No Known Activations