INDEX

Explanations

words related to sports environments, specifically focusing on the ice or court

oai_token-act-pair · gpt-3.5-turbo

locations related to sports activity surfaces

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ortium

-0.73

oras

-0.72

laus

-0.65

ett

-0.64

 warr

-0.62

 Telesc

-0.61

itarian

-0.61

UCS

-0.59

IG

-0.59

 href

-0.59

POSITIVE LOGITS

 podium

0.94

plays

0.83

waves

0.81

 floor

0.79

walk

0.78

 unnoticed

0.75

 sideline

0.73

keepers

0.73

 sidelines

0.72

pter

0.72

Activations Density 0.151%

words related to sports environments, specifically focusing on the ice or court

locations related to sports activity surfaces

No Comments

No Known Activations