INDEX

Explanations

specific foreign names and terms used in a text

oai_token-act-pair · gpt-3.5-turbo

characters, symbols, or non-standard sequences in a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 psychiat

-0.62

 Stain

-0.61

 plantation

-0.60

 Abbey

-0.59

 pasture

-0.58

asar

-0.56

Detailed

-0.54

ADRA

-0.54

GBT

-0.54

FU

-0.53

POSITIVE LOGITS

ilver

0.82

etus

0.70

spir

0.69

irin

0.67

anmar

0.67

 Favor

0.66

lication

0.65

imgur

0.64

vu

0.63

otech

0.63

Activations Density 0.195%

specific foreign names and terms used in a text

characters, symbols, or non-standard sequences in a text

No Comments

No Known Activations