INDEX

Explanations

numerical values that stand out

oai_token-act-pair · gpt-3.5-turbo

numbers and numerical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 challeng

-0.74

 newsp

-0.73

 empt

-0.73

 travers

-0.72

 fert

-0.72

 explos

-0.69

 administr

-0.69

 manif

-0.68

 leve

-0.67

 climax

-0.67

POSITIVE LOGITS

 ILCS

1.18

 SHARES

1.05

0.86

NCT

0.84

0.83

0.82

Activations Density 0.080%

numerical values that stand out

numbers and numerical data

No Comments

No Known Activations