INDEX

Explanations

descriptions of specific incidents involving individuals in various settings, particularly in relation to unusual encounters or activities

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Cfr

-0.80

 embodi

-0.76

 secon

-0.76

 alre

-0.75

 unden

-0.74

 increa

-0.71

fta

-0.70

 wherea

-0.69

oun

-0.69

 sovere

-0.69

POSITIVE LOGITS

twimg

0.64

 momentarily

0.59

 unattended

0.58

toPromise

0.55

 briefly

0.54

 Normdatei

0.54

ConstraintMaker

0.53

 leaving

0.52

 leave

0.52

lccccc

0.52

Activations Density 0.300%

descriptions of specific incidents involving individuals in various settings, particularly in relation to unusual encounters or activities

No Comments

No Known Activations