INDEX

Explanations

references to time durations, specifically mentioning "weeks."

oai_token-act-pair · gpt-3.5-turbo

references to a specific duration of time, particularly in weeks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

inav

-0.79

cellence

-0.67

inite

-0.66

ech

-0.65

Reviewer

-0.61

 suspic

-0.60

XXXX

-0.60

gio

-0.60

acted

-0.60

pend

-0.59

POSITIVE LOGITS

days

1.01

ago

0.96

 gestation

0.88

night

0.85

DAY

0.84

Ago

0.82

uda

0.77

iversary

0.77

uary

0.76

alez

0.74

Activations Density 0.043%

references to time durations, specifically mentioning "weeks."

references to a specific duration of time, particularly in weeks

No Comments

No Known Activations