INDEX

Explanations

text related to annual events or occurrences

oai_token-act-pair · gpt-3.5-turbo

mentions of annual events or occurrences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

holes

-0.84

 Handler

-0.81

wright

-0.72

UTF

-0.71

agra

-0.67

hole

-0.67

utf

-0.64

Ì¶

-0.64

yer

-0.63

ening

-0.63

POSITIVE LOGITS

 annual

0.90

ized

0.89

ised

0.81

ãĥ¼ãĥĨãĤ£

0.80

ivals

0.79

 yearly

0.79

 Annual

0.77

ãĥ£

0.76

è¦ļéĨĴ

0.74

cies

0.73

Activations Density 0.015%

text related to annual events or occurrences

mentions of annual events or occurrences

No Comments

No Known Activations