INDEX

Explanations

references to legal situations or actions

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

 disagre

-2.09

 shenan

-2.08

 encomp

-2.01

 increa

-2.00

 milf

-2.00

 reluct

-2.00

 depic

-1.99

 inev

-1.96

 impra

-1.96

 affor

-1.92

POSITIVE LOGITS

 مرئيه

0.82

رشف

0.77

 typelib

0.77

SequentialGroup

0.77

 सत्यापित

0.74

CppCodeGen

0.73

دانشنامهٔ

0.72

RemoveField

0.71

MockBean

0.71

 MessageBoxIcon

0.71

Activations Density 0.795%

references to legal situations or actions

No Comments

No Known Activations