INDEX

Explanations

references to specific events, deals, or tests

oai_token-act-pair · gpt-3.5-turbo

key concepts and terms related to events, conditions, and classifications

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

å§«

-0.89

 virtues

-0.71

 channels

-0.71

 Methods

-0.71

doms

-0.68

 scenes

-0.68

 Machines

-0.68

 departments

-0.66

akings

-0.66

Frames

-0.66

POSITIVE LOGITS

ifier

0.89

 consisting

0.87

elist

0.78

 akin

0.78

cko

0.75

 similar

0.74

forcer

0.72

 lookup

0.71

robe

0.71

 named

0.70

Activations Density 0.584%

references to specific events, deals, or tests

key concepts and terms related to events, conditions, and classifications

No Comments

No Known Activations