INDEX

Explanations

names of individuals, potentially famous or influential

oai_token-act-pair · gpt-3.5-turbo

names or surnames of individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

udeb

-0.70

soDeliveryDate

-0.67

FactoryReloaded

-0.66

 governors

-0.63

 modifiers

-0.63

 demoral

-0.63

Plex

-0.62

 shorth

-0.61

 legitimacy

-0.61

ADRA

-0.61

POSITIVE LOGITS

Jr

1.32

Sr

0.99

III

0.95

(@

0.92

nen

0.88

chuk

0.86

owski

0.86

sson

0.85

 writes

0.84

zyk

0.83

Activations Density 0.287%

names of individuals, potentially famous or influential

names or surnames of individuals

No Comments

No Known Activations