INDEX

Explanations

words related to sensitivity to various factors

oai_token-act-pair · gpt-3.5-turbo

terms related to sensitivity in various contexts

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

unks

-0.70

Pry

-0.70

thing

-0.70

liam

-0.70

beat

-0.66

vm

-0.65

Ame

-0.65

 Roads

-0.65

 Vale

-0.64

oran

-0.63

POSITIVE LOGITS

 sensitivity

4.06

 sensit

2.64

ensitivity

2.34

 sensitive

1.97

 responsiveness

1.77

 specificity

1.77

 insensitive

1.60

 tolerance

1.60

sensitive

1.56

 susceptibility

1.46

Activations Density 0.018%

words related to sensitivity to various factors

terms related to sensitivity in various contexts

No Comments

No Known Activations