INDEX

Explanations

references to notable people and their works, such as actors, authors, and their related projects

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

 rispond

-1.05

 scopri

-1.03

 parteci

-1.03

 dimenti

-1.02

 purtroppo

-0.98

 vediamo

-0.91

 migli

-0.90

 conosce

-0.89

 anzi

-0.88

 interessa

-0.87

POSITIVE LOGITS

 unspeak

1.13

 indescri

1.03

 vainly

1.03

 impra

1.03

 gaily

1.00

 inconce

0.96

 apprehen

0.95

 ineffec

0.95

 horrend

0.94

 disagre

0.92

Activations Density 0.579%

references to notable people and their works, such as actors, authors, and their related projects

No Comments

No Known Activations