INDEX

Explanations

the word "keen."

oai_token-act-pair · gpt-3.5-turbo

the term 'keen' indicating a strong interest or enthusiasm

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ä»£

-0.81

ICAN

-0.73

channelAvailability

-0.71

AGE

-0.68

anuts

-0.66

utions

-0.61

 Myst

-0.61

inventoryQuantity

-0.60

 Frankenstein

-0.60

 Incarn

-0.60

POSITIVE LOGITS

ly

1.03

 keen

0.99

eful

0.97

ness

0.94

emouth

0.85

irection

0.77

entimes

0.76

 Interest

0.74

mares

0.73

sonian

0.72

Activations Density 0.010%

the word "keen."

the term 'keen' indicating a strong interest or enthusiasm

No Comments

No Known Activations