INDEX

Explanations

times expressed in hours with the specific time, such as "eight o'clock" or "ten o'clock."

oai_token-act-pair · gpt-3.5-turbo

references to time, particularly clock times

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

sels

-0.83

du

-0.78

shared

-0.72

ebook

-0.72

sche

-0.71

ifferent

-0.69

itably

-0.69

won

-0.67

Sov

-0.67

 Schwar

-0.67

POSITIVE LOGITS

wise

0.93

urnal

0.87

inois

0.87

iculty

0.85

ayson

0.83

agascar

0.79

ousand

0.76

CLASSIFIED

0.74

 vigil

0.73

uminati

0.71

Activations Density 0.022%

times expressed in hours with the specific time, such as "eight o'clock" or "ten o'clock."

references to time, particularly clock times

No Comments

No Known Activations