INDEX

Explanations

numbers or numerical patterns within the text

oai_token-act-pair · gpt-3.5-turbo

numeric references, particularly in relation to voting or statistical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gart

-0.67

 tremend

-0.66

ierrez

-0.64

iques

-0.64

 belly

-0.63

anguage

-0.62

anamo

-0.61

 avail

-0.59

enhagen

-0.57

spread

-0.57

POSITIVE LOGITS

0.95

0.92

0.91

0.89

0.87

 Reasons

0.86

0.84

Activations Density 0.080%

numbers or numerical patterns within the text

numeric references, particularly in relation to voting or statistical data

No Comments

No Known Activations