INDEX

Explanations

transportation-related terms, especially relating to trains and railways

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

proper names or acronyms (like LRT, Lyndon Johnson, LFS253, Lockheed Martin).

oai_token-act-pair · claude-3-7-sonnet-20250219 Triggered by @eekay

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lné

-0.52

öffel

-0.51

 Abbiamo

-0.47

 Tienes

-0.46

 Altri

-0.45

Xoa

-0.45

 trataba

-0.45

 Ogni

-0.44

 Aucune

-0.44

 continuant

-0.44

POSITIVE LOGITS

0.67

LK

0.66

0.62

LB

0.62

Laj

0.62

LN

0.60

Ls

0.60

LM

0.60

lw

0.60

LQ

0.59

Activations Density 0.711%

transportation-related terms, especially relating to trains and railways

proper names or acronyms (like LRT, Lyndon Johnson, LFS253, Lockheed Martin).

No Comments

No Known Activations