INDEX

Explanations

words related to controllers, especially in the context of gaming

oai_token-act-pair · gpt-3.5-turbo

references to gaming controllers

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

ews

-0.87

olit

-0.74

iary

-0.73

entimes

-0.72

 Ruff

-0.66

onym

-0.65

ened

-0.64

inx

-0.64

 Graham

-0.63

 Fraz

-0.63

POSITIVE LOGITS

 controller

0.79

rollers

0.75

Deploy

0.74

pad

0.73

controller

0.73

wright

0.71

washer

0.71

eers

0.70

SHIP

0.70

Focus

0.70

Activations Density 0.017%

words related to controllers, especially in the context of gaming

references to gaming controllers

No Comments

No Known Activations