INDEX

Explanations

names of individuals or places

oai_token-act-pair · gpt-3.5-turbo

proper nouns and names of individuals or entities

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

erella

-0.66

reviewed

-0.63

ateurs

-0.61

glers

-0.60

WT

-0.60

nesday

-0.60

anchester

-0.59

ruary

-0.58

called

-0.57

 Egyptians

-0.57

POSITIVE LOGITS

ibrary

0.79

ĪĴ

0.74

Pwr

0.67

adi

0.65

 è£ıè

0.65

nih

0.64

intel

0.64

zu

0.64

fen

0.61

schild

0.60

Activations Density 0.886%

names of individuals or places

proper nouns and names of individuals or entities

No Comments

No Known Activations