INDEX

Explanations

information related to medical centers or research institutions

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>

-3.08

<?

-0.88

 gratify

-0.83

/***

-0.82

ⓧ

-0.78

 endow

-0.74

<?

-0.74

 heighten

-0.74

 magnify

-0.74

 rehabilitate

-0.72

POSITIVE LOGITS

 Center

1.18

 center

1.13

Center

1.11

 maksi

1.09

 CENTER

1.05

 seksi

1.02

Centers

1.01

 centers

1.00

 Centers

1.00

center

0.99

Activations Density 0.110%

information related to medical centers or research institutions

No Comments

No Known Activations