INDEX

Explanations

timestamps in the format of hours and minutes

oai_token-act-pair · gpt-3.5-turbo

timestamps and date information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

Ĥİ

-0.70

gently

-0.67

©¶æ

-0.64

 doub

-0.61

 Kirin

-0.59

 mould

-0.56

 analys

-0.55

 endors

-0.53

 differentiated

-0.53

 Norn

-0.53

POSITIVE LOGITS

IST

1.09

PDT

0.79

 Views

0.78

EDT

0.75

GMT

0.74

PST

0.72

 Nanto

0.71

UTC

0.71

pm

0.68

Thu

0.65

Activations Density 0.067%

timestamps in the format of hours and minutes

timestamps and date information

No Comments

No Known Activations