INDEX

Explanations

dates expressed in a specific format, mainly in the context of statistics or reports

oai_token-act-pair · gpt-3.5-turbo

temporal references and time-related statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

drm

-0.75

ãĤ¤ãĥĪ

-0.74

forts

-0.70

Synopsis

-0.69

Appearance

-0.69

orge

-0.67

ãĤ¦ãĤ¹

-0.67

inges

-0.66

cffffcc

-0.65

matter

-0.65

POSITIVE LOGITS

 there

1.04

 according

1.04

 total

0.97

according

0.92

 median

0.90

0.89

 average

0.88

0.87

Activations Density 0.210%

dates expressed in a specific format, mainly in the context of statistics or reports

temporal references and time-related statistics

No Comments

No Known Activations