INDEX

Explanations

words related to sports positions and activities

oai_token-act-pair · gpt-3.5-turbo

words that describe various roles or 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

sembly

-0.86

ĸļ

-0.85

chwitz

-0.83

ournal

-0.80

schild

-0.73

uration

-0.73

 correspond

-0.68

aeda

-0.68

enthal

-0.67

ensable

-0.67

POSITIVE LOGITS

 extraord

1.13

gery

0.80

hawks

0.80

 beware

0.77

oute

0.77

 derby

0.77

wolves

0.72

ds

0.72

oom

0.70

digy

0.70

Activations Density 0.074%

words related to sports positions and activities

words that describe various roles or positions in sports

No Comments

No Known Activations