INDEX

Explanations

locations followed by a date as in a news article

oai_token-act-pair · gpt-3.5-turbo

punctuation marks, specifically periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ogen

-0.71

ETF

-0.68

disk

-0.66

stal

-0.65

INAL

-0.65

IME

-0.65

orical

-0.63

itia

-0.63

omed

-0.63

imus

-0.61

POSITIVE LOGITS

uits

0.76

taboola

0.67

DAQ

0.66

nesday

0.65

imentary

0.61

adena

0.60

 Calais

0.60

ahoo

0.60

nels

0.59

lication

0.59

Activations Density 0.035%

locations followed by a date as in a news article

punctuation marks, specifically periods

No Comments

No Known Activations