INDEX

Explanations

mentions of locations or geographical features

oai_token-act-pair · gpt-3.5-turbo

terms related to various types of lands and ecological environments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

berus

-0.75

MENT

-0.67

agall

-0.66

athetic

-0.65

aple

-0.65

thumbnails

-0.64

inventoryQuantity

-0.60

 logical

-0.60

ebus

-0.59

NING

-0.59

POSITIVE LOGITS

dale

0.99

wagen

0.92

borough

0.92

creen

0.91

lands

0.89

terday

0.88

boro

0.88

hips

0.87

 challeng

0.87

mere

0.86

Activations Density 0.019%

mentions of locations or geographical features

terms related to various types of lands and ecological environments

No Comments

No Known Activations