INDEX

Explanations

time-related expressions

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate a sense of time or sequence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

YD

-0.67

OTUS

-0.66

say

-0.65

cia

-0.65

employed

-0.64

forts

-0.63

nu

-0.62

STER

-0.62

 Sloan

-0.62

inet

-0.62

POSITIVE LOGITS

wards

0.73

oard

0.70

 persecut

0.68

udeau

0.67

ctors

0.65

©¶æ

0.64

etheless

0.63

ħĭ

0.59

 agon

0.58

 manner

0.58

Activations Density 0.182%

time-related expressions

phrases that indicate a sense of time or sequence

No Comments

No Known Activations