INDEX

Explanations

time-related durations, like "years" or "months" spent doing something

oai_token-act-pair · gpt-3.5-turbo

time durations and periods associated with experiences or events

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

ipper

-0.61

 ceilings

-0.61

stood

-0.60

rium

-0.59

awed

-0.59

strength

-0.58

ĭ

-0.56

ippy

-0.56

ogle

-0.55

circle

-0.55

POSITIVE LOGITS

 studying

0.72

izabeth

0.70

 researching

0.68

onding

0.68

cation

0.68

 wondering

0.67

 livest

0.66

 photograp

0.65

pher

0.64

sterdam

0.64

Activations Density 0.071%

time-related durations, like "years" or "months" spent doing something

time durations and periods associated with experiences or events

No Comments

No Known Activations