INDEX

Explanations

phrases related to technical instructions or guides

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>

-1.51

 intersper

-1.43

 xxvi

-1.13

 gaily

-1.11

 xxii

-1.09

 xxiii

-1.08

 encomp

-1.07

 gratify

-1.06

 unspeak

-1.06

xxv

-1.05

POSITIVE LOGITS

sl

1.19

SL

1.16

SL

1.09

sl

1.09

Sl

1.07

Sl

1.03

gl

0.81

PSL

0.76

kl

0.75

FL

0.72

Activations Density 0.491%

phrases related to technical instructions or guides

No Comments

No Known Activations