INDEX

Explanations

terms related to specific geographical locations

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

<bos>

-0.88

PhysRevD

-0.77

<>

-0.75

setToolTipText

-0.72

 himo

-0.72

JRadioButton

-0.70

localPosition

-0.70

SneakyThrows

-0.69

DataPropertyName

-0.69

GenerationType

-0.68

POSITIVE LOGITS

 impra

1.53

 encomp

1.53

 secon

1.49

 eiffel

1.48

 alre

1.47

 increa

1.45

 Confu

1.44

fuf

1.43

 intersper

1.43

 depic

1.40

Activations Density 0.516%

terms related to specific geographical locations

No Comments

No Known Activations