INDEX

Explanations

terms related to recovery and rebuilding efforts after a disaster

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>

-3.18

let

-0.72

<?

-0.69

setClass

-0.69

 lệ

-0.68

 AssemblyCompany

-0.68

put

-0.68

ldc

-0.66

led

-0.66

-0.65

POSITIVE LOGITS

 bandung

2.07

 wien

1.92

 stockholm

1.92

 thut

1.90

 dises

1.88

 jaya

1.85

aen

1.83

 increa

1.78

 maneu

1.77

ftu

1.76

Activations Density 0.120%

terms related to recovery and rebuilding efforts after a disaster

No Comments

No Known Activations