INDEX

Explanations

words related to physical attributes or features

oai_token-act-pair · gpt-3.5-turbo

terms and concepts related to measurement and evaluation

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ento

-0.58

 Accountability

-0.57

ETF

-0.56

 Balanced

-0.54

 heterogeneity

-0.52

Examples

-0.51

Contract

-0.50

Policy

-0.50

 baseline

-0.50

"""

-0.48

POSITIVE LOGITS

 guiActiveUn

0.79

 mast

0.63

lled

0.63

icago

0.62

 unfocusedRange

0.58

wered

0.58

ãĥ¥

0.55

lessly

0.54

 carbs

0.54

reet

0.53

Activations Density 1.694%

words related to physical attributes or features

terms and concepts related to measurement and evaluation

No Comments

No Known Activations