INDEX

Explanations

subjects related to comparison, analysis, and evaluation

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

 honn

-0.59

 Mère

-0.59

 chande

-0.59

 malheureux

-0.58

 cardin

-0.57

 sembl

-0.56

 pinak

-0.55

 kanya

-0.54

 debout

-0.54

 soigne

-0.54

POSITIVE LOGITS

 instead

0.58

 focus

0.57

 replace

0.56

 embrace

0.55

spesies

0.55

 replaced

0.54

 preferring

0.54

 vervangen

0.53

 Instead

0.53

 concentrate

0.53

Activations Density 0.385%

subjects related to comparison, analysis, and evaluation

No Comments

No Known Activations