INDEX

Explanations

names of football players

oai_token-act-pair · gpt-3.5-turbo

commas in lists of names or positions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

ipedia

-0.72

ageddon

-0.68

agara

-0.67

taining

-0.66

 conventions

-0.65

 inertia

-0.64

agate

-0.63

omen

-0.63

nces

-0.62

ember

-0.61

POSITIVE LOGITS

RB

1.72

QB

1.70

CB

1.63

LB

1.62

WR

1.60

DB

1.52

OL

1.48

DT

1.48

DL

1.45

TE

1.44

Activations Density 0.049%

names of football players

commas in lists of names or positions

No Comments

No Known Activations