INDEX

Explanations

terms related to tools and cutting in the context of barriers or breaches

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

chanind/openwebtext-gemma

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

ctigges/openwebtext-gemma-1024-cl

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

<bos>

-2.27

 solidar

-0.96

 anse

-0.88

 stoff

-0.82

 dras

-0.81

 vern

-0.81

 geograf

-0.80

gie

-0.79

 praktik

-0.79

 gesta

-0.79

POSITIVE LOGITS

 carrefour

1.25

 pymysql

1.11

 sentier

1.09

 swarovski

1.08

 fameux

1.07

 ecru

1.07

 docteur

1.06

 vété

1.05

 créateur

1.04

 prêtre

1.01

Activations Density 0.493%

terms related to tools and cutting in the context of barriers or breaches

No Known Activations