INDEX

Explanations

phrases related to sports events and activities

oai_token-act-pair · gpt-3.5-turbo

terms related to game statistics and performance metrics

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hirt

-0.81

utsche

-0.76

eret

-0.75

SourceFile

-0.74

catentry

-0.72

ractive

-0.70

ierre

-0.68

ollar

-0.66

outhern

-0.66

abase

-0.65

POSITIVE LOGITS

 guiActiveUnfocused

0.73

estyles

0.71

 forfeit

0.64

TAG

0.64

 preseason

0.62

rollers

0.62

 Thrones

0.60

 iPads

0.60

 Gladiator

0.59

 Marin

0.59

Activations Density 0.444%

phrases related to sports events and activities

terms related to game statistics and performance metrics

No Comments

No Known Activations