INDEX

Explanations

phrases related to football positions, particularly the quarterback position

oai_token-act-pair · gpt-3.5-turbo

mentions of various player positions in sports

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

 Warn

-0.79

Interstitial

-0.79

vous

-0.78

cause

-0.71

isks

-0.68

anz

-0.66

enos

-0.66

Episode

-0.65

 Jinn

-0.63

bey

-0.63

POSITIVE LOGITS

 positions

0.96

 position

0.88

 vacated

0.83

atile

0.83

ichick

0.75

 roles

0.74

ally

0.73

 shif

0.72

 positional

0.72

idable

0.72

Activations Density 0.027%

phrases related to football positions, particularly the quarterback position

mentions of various player positions in sports

No Comments

No Known Activations