INDEX

Explanations

descriptions of visual scenes and situations involving perception and recognition

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

 perfet

-1.04

 strick

-1.02

 purcha

-1.02

 nece

-1.01

 excru

-1.01

 madonna

-1.01

 lamborghini

-0.98

 embra

-0.98

 peppa

-0.97

 panama

-0.97

POSITIVE LOGITS

 familiar

0.57

 something

0.53

 empty

0.52

 parked

0.52

ENODEV

0.52

 someone

0.51

 huge

0.51

 tall

0.51

 sign

0.51

 large

0.50

Activations Density 0.367%

descriptions of visual scenes and situations involving perception and recognition

No Comments

No Known Activations