INDEX

Explanations

text related to linguistic theory and grammatical principles

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

HuggingFaceFW/fineweb

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-1.07

ⓧ

-0.92

iddhar

-0.81

 Mlle

-0.78

 quitted

-0.77

/**

-0.75

 hentai

-0.75

 disambigu

-0.73

 shenan

-0.71

 gild

-0.67

POSITIVE LOGITS

 parameter

1.22

parameter

1.20

Parameter

1.16

 Parameter

1.14

 param

1.11

 parameters

1.11

Param

1.11

 Param

1.09

parameters

1.08

PARAM

1.04

Activations Density 0.411%

text related to linguistic theory and grammatical principles

No Comments

No Known Activations