INDEX

Explanations

specific terms or phrases related to technical protocols and legal cases

oai_token-act-pair · gpt-3.5-turbo

references to specific organizations or trademarks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.71

 Samoa

-0.70

 Columb

-0.70

lihood

-0.69

 seriousness

-0.66

ãĥī

-0.64

 Sacrament

-0.63

 Greenland

-0.63

âĶĢâĶĢ

-0.63

thus

-0.63

POSITIVE LOGITS

RF

1.01

RF

0.94

senal

0.89

andom

0.88

raid

0.82

YL

0.80

UL

0.77

 shielding

0.77

 tremend

0.77

velength

0.76

Activations Density 0.007%

specific terms or phrases related to technical protocols and legal cases

references to specific organizations or trademarks

No Comments

No Known Activations