INDEX

Explanations

expressions of apology or regret

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.78

 Walkover

-1.04

 bezeichneter

-1.01

 himo

-1.01

CreateModel

-0.92

HasIndex

-0.92

CreateIndex

-0.86

Xar

-0.81

millimeters

-0.81

ObjectModel

-0.81

POSITIVE LOGITS

 maneu

3.09

 reluct

3.04

 increa

3.02

 affor

3.01

 shenan

2.99

 impra

2.97

 disagre

2.86

 indestru

2.83

 scrat

2.78

 excru

2.78

Activations Density 0.547%

expressions of apology or regret

No Comments

No Known Activations