INDEX

Explanations

text related to job creation, job loss, employment policies, and unemployment

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-4.01

 intersper

-1.50

/***

-1.17

 reconno

-1.08

 shenan

-1.07

 encomp

-1.04

 endow

-1.03

-0.97

 incarcer

-0.96

 naï

-0.93

POSITIVE LOGITS

 bandung

1.00

 marea

0.91

 masaj

0.90

 riva

0.88

capulco

0.87

 corrom

0.87

 caccia

0.86

 montagna

0.85

 ristor

0.84

 maroc

0.84

Activations Density 5.671%

text related to job creation, job loss, employment policies, and unemployment

No Comments

No Known Activations