INDEX

Explanations

phrases related to step-by-step processes or actions in a narrative

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 reluct

-0.93

 intersper

-0.92

 apprehen

-0.90

 increa

-0.89

 inev

-0.88

 unspeak

-0.85

 strick

-0.84

 attemp

-0.80

 disagre

-0.80

 exorbit

-0.78

POSITIVE LOGITS

except

0.70

<bos>

0.67

 except

0.66

audiovisuel

0.64

Except

0.64

 including

0.63

 INCLUDING

0.59

 censiti

0.58

 entire

0.57

including

0.57

Activations Density 0.294%

phrases related to step-by-step processes or actions in a narrative

No Comments

No Known Activations