INDEX

Explanations

dates and locations

oai_token-act-pair · gpt-3.5-turbo

commas in a list of geographic locations and dates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

osexual

-0.67

selves

-0.65

itionally

-0.64

enary

-0.64

onym

-0.64

ioned

-0.63

iral

-0.62

SQL

-0.62

ado

-0.61

VERTISEMENT

-0.60

POSITIVE LOGITS

 Calif

0.94

 District

0.85

 Borough

0.82

atche

0.81

 Colo

0.79

 County

0.78

 suburb

0.77

Fla

0.77

Ala

0.76

 where

0.76

Activations Density 0.227%

dates and locations

commas in a list of geographic locations and dates

No Comments

No Known Activations