INDEX

Explanations

references to technical models or designations

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

 NavBar

-0.58

 dramatist

-0.57

 UserData

-0.55

 ApiService

-0.55

 useAuth

-0.54

lizabeth

-0.53

 actionTypes

-0.53

 sympy

-0.53

 psycopg

-0.51

 laissant

-0.50

POSITIVE LOGITS

 model

1.42

model

1.37

 Model

1.37

 MODEL

1.35

 models

1.30

Model

1.28

MODEL

1.27

 Models

1.22

models

1.15

 MODELS

1.11

Activations Density 0.066%

references to technical models or designations

No Comments

No Known Activations