INDEX

Explanations

locations or places mentioned in a text

oai_token-act-pair · gpt-3.5-turbo

references to a specific fictional location and associated entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

xual

-0.99

sembly

-0.86

terday

-0.86

eering

-0.78

 belts

-0.76

ffen

-0.72

umenthal

-0.70

 compr

-0.68

ignty

-0.67

 presentation

-0.67

POSITIVE LOGITS

Nob

0.85

bits

0.85

neys

0.84

ome

0.82

acity

0.81

loo

0.78

spot

0.77

acles

0.77

keeper

0.77

bott

0.75

Activations Density 0.047%

locations or places mentioned in a text

references to a specific fictional location and associated entities

No Comments

No Known Activations