INDEX

Explanations

keywords related to the concept of evaluating, judging, or assessing something

oai_token-act-pair · gpt-3.5-turbo

gerunds and actions related to assessment and evaluation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

pim

-0.58

 amended

-0.57

 Virus

-0.57

 tasted

-0.57

pox

-0.54

 contributed

-0.54

 consolidated

-0.54

 objected

-0.53

 modified

-0.53

pes

-0.52

POSITIVE LOGITS

lighting

1.76

asuring

1.74

imating

1.69

orting

1.65

ribing

1.64

igating

1.64

etting

1.63

ulating

1.62

angering

1.61

icing

1.61

Activations Density 0.070%

keywords related to the concept of evaluating, judging, or assessing something

gerunds and actions related to assessment and evaluation

No Comments

No Known Activations