INDEX

Explanations

reports and studies

oai_token-act-pair · gpt-3.5-turbo

references to studies or reports related to policy and research findings

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

ulkan

-0.71

alogue

-0.70

talk

-0.68

Termin

-0.68

atics

-0.67

FIELD

-0.67

 artic

-0.67

agall

-0.67

 maple

-0.66

 transporter

-0.65

POSITIVE LOGITS

 Scientific

0.76

study

0.75

 Nasa

0.72

 commissioned

0.69

 Starr

0.68

Study

0.68

published

0.67

 titled

0.67

 National

0.67

 statistical

0.66

Activations Density 0.301%

reports and studies

references to studies or reports related to policy and research findings

No Comments

No Known Activations