INDEX

Explanations

mentions of the word 'lion' and related terms

oai_token-act-pair · gpt-3.5-turbo

references to lions

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

mble

-0.85

chell

-0.76

ilk

-0.76

Ñı

-0.74

lying

-0.73

matter

-0.70

aeda

-0.69

ACTION

-0.67

ÑĮ

-0.67

skirts

-0.64

POSITIVE LOGITS

esses

1.28

fish

1.10

 lions

1.09

ess

1.01

eye

0.98

ous

0.94

 lion

0.94

osaurs

0.92

odon

0.91

toe

0.81

Activations Density 0.016%

mentions of the word 'lion' and related terms

references to lions

No Comments

No Known Activations