INDEX

Explanations

phrases related to throwing actions

oai_token-act-pair · gpt-3.5-turbo

phrases related to "throwing" or taking action towards something or someone

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ÃŁ

-0.76

Eva

-0.73

CLA

-0.71

DA

-0.70

appa

-0.70

yrights

-0.69

inez

-0.68

ieth

-0.68

Upload

-0.67

emis

-0.66

POSITIVE LOGITS

 overboard

1.44

 tant

1.16

 wrench

1.05

 grenades

1.02

 towel

0.99

 darts

0.96

 punches

0.92

 grenade

0.90

 contrace

0.87

 dice

0.81

Activations Density 0.087%

phrases related to throwing actions

phrases related to "throwing" or taking action towards something or someone

No Comments

No Known Activations