INDEX

Explanations

mentions of legal terms related to divorce

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

HuggingFaceFW/fineweb

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.14

ⓧ

-0.59

Ngoài

-0.58

IBOutlet

-0.57

Hochspringen

-0.57

Màu

-0.53

/*!

-0.52

 pinned

-0.50

 warn

-0.49

됐

-0.49

POSITIVE LOGITS

Juf

1.28

Divorce

1.13

 divorce

1.11

 Divorce

1.10

 jaya

1.08

 Minang

1.08

 bandung

1.06

 Jambi

1.05

Hæ

1.04

 Banjar

1.04

Activations Density 0.224%

mentions of legal terms related to divorce

No Comments

No Known Activations