INDEX

Explanations

words related to legal or policy matters

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

However

-0.51

muer

-0.45

trà

-0.45

Poli

-0.44

balo

-0.44

riba

-0.44

kuper

-0.44

 However

-0.44

however

-0.43

Mat

-0.42

POSITIVE LOGITS

 mondeo

0.71

 stickied

0.66

 geforce

0.64

/**

0.62

 avenger

0.62

 souffrance

0.60

 fortnite

0.60

 jetta

0.58

 zelda

0.58

Activations Density 0.284%

words related to legal or policy matters

No Comments

No Known Activations