INDEX

Explanations

vocabulary related to frames or framing

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>

-3.03

ⓧ

-0.77

/***

-0.70

 inaugurate

-0.69

 endow

-0.62

<?

-0.61

MarshalTo

-0.61

 endeavored

-0.59

 rehabilitate

-0.59

POSITIVE LOGITS

 Frame

1.28

 frame

1.27

 Frames

1.27

 frames

1.25

 saar

1.17

frame

1.16

Frame

1.15

 thuy

1.14

 kark

1.11

 FRAME

1.11

Activations Density 0.069%

vocabulary related to frames or framing

No Comments

No Known Activations