INDEX

Explanations

locations or geographical entities

oai_token-act-pair · gpt-3.5-turbo

conjunctions and references to specific geographic locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

icz

-0.83

ugi

-0.82

hiba

-0.79

votes

-0.79

ovie

-0.74

oslav

-0.70

itsch

-0.69

soDeliveryDate

-0.69

gets

-0.69

ictive

-0.69

POSITIVE LOGITS

 Labrador

0.84

 furthermore

0.71

 arrow

0.69

 Caucasus

0.65

APTER

0.64

 mortar

0.63

 thence

0.63

 Wales

0.60

 Clyde

0.60

 Forestry

0.60

Activations Density 0.176%

locations or geographical entities

conjunctions and references to specific geographic locations

No Comments

No Known Activations