INDEX

Explanations

information related to specific locations or landmarks

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

 massacres

-0.96

corruption

-0.87

 atrocities

-0.86

 bombings

-0.86

 insurgents

-0.85

 disinformation

-0.84

 insurgency

-0.84

ABORT

-0.82

ायर

-0.81

 fascism

-0.80

POSITIVE LOGITS

<bos>

16.51

expandindo

2.52

GEBURTSDATUM

2.46

 encomp

2.43

 intersper

2.40

 betweenstory

2.36

 dispen

2.32

Autoritní

2.32

fuf

2.28

 Administrativna

2.27

Activations Density 0.781%

information related to specific locations or landmarks

No Comments

No Known Activations