INDEX

Explanations

mentions of facilities or places related to specific functions or activities

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>

-2.79

/***

-1.00

ⓧ

-0.87

 intersper

-0.81

 endow

-0.79

/**

-0.78

 amass

-0.73

 oppress

-0.72

 disbur

-0.71

 inaugurate

-0.71

POSITIVE LOGITS

 facility

1.24

 lele

1.21

 Facility

1.21

 Facilities

1.17

 facilities

1.17

 kasa

1.15

 maksi

1.12

Facilities

1.11

 naer

1.11

Facility

1.11

Activations Density 0.027%

mentions of facilities or places related to specific functions or activities

No Comments

No Known Activations