INDEX

Explanations

mentions or references related to sports events or athletes

oai_token-act-pair · gpt-3.5-turbo

references to All-Star designations in sports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

alys

-0.79

perm

-0.77

hr

-0.74

»Ĵ

-0.72

haar

-0.72

ĸļ

-0.72

fw

-0.69

²¾

-0.69

okia

-0.68

Ã¶r

-0.68

POSITIVE LOGITS

 Baseball

0.80

osterone

0.76

NBA

0.72

 Winners

0.71

 caliber

0.70

Hon

0.69

 Weekend

0.69

 Athlet

0.68

dom

0.68

 Celebrity

0.67

Activations Density 0.027%

mentions or references related to sports events or athletes

references to All-Star designations in sports

No Comments

No Known Activations