INDEX

Explanations

series or multi-part works

oai_token-act-pair · gpt-3.5-turbo

references to parts or segments of a series

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

kefeller

-0.78

berus

-0.71

incinn

-0.67

anyon

-0.66

avorite

-0.63

olla

-0.62

anca

-0.61

HAEL

-0.60

jriwal

-0.60

urses

-0.59

POSITIVE LOGITS

icular

1.22

icles

1.13

icle

1.10

ners

1.09

meal

1.04

ridge

1.00

isans

0.99

nered

0.98

ition

0.97

ner

0.95

Activations Density 0.027%

series or multi-part works

references to parts or segments of a series

No Comments

No Known Activations