INDEX

Explanations

mentions of names or entities in a sentence

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

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 reluct

-1.21

 encomp

-1.14

 inev

-1.13

 impra

-1.11

 pamph

-1.11

 disagre

-1.10

 accla

-1.10

 apprehen

-1.09

 emphat

-1.08

 increa

-1.05

POSITIVE LOGITS

 specifics

0.81

 specific

0.78

 exact

0.72

specific

0.69

angliski

0.65

 cụ

0.63

具体的

0.63

具体

0.63

 specifically

0.63

nor

0.63

Activations Density 0.224%

mentions of names or entities in a sentence

No Comments

No Known Activations