INDEX

Explanations

numerical values or measurements in a text

oai_token-act-pair · gpt-3.5-turbo

numerical values and statistics

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

 disadvant

-0.74

 Vaugh

-0.71

 Nieto

-0.68

ierrez

-0.68

srf

-0.66

anamo

-0.65

romeda

-0.62

senal

-0.62

agine

-0.62

 undermin

-0.61

POSITIVE LOGITS

th

0.72

0.71

0.70

0.68

0.67

 Minutes

0.67

RF

0.67

Activations Density 0.210%

numerical values or measurements in a text

numerical values and statistics

No Comments

No Known Activations