INDEX

Explanations

phrases related to specific durations or time intervals

oai_token-act-pair · gpt-3.5-turbo

references to time periods, specifically the word "years" and its occurrences

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

IFrame

Link

Negative Logits

 redes

-0.68

Mat

-0.66

Values

-0.65

icc

-0.62

 Moons

-0.60

 Strongh

-0.59

 Tears

-0.58

VALUE

-0.58

 sarc

-0.57

 slips

-0.57

POSITIVE LOGITS

ago

0.82

âĢ²

0.78

 olds

0.74

ynski

0.72

hips

0.70

SPONSORED

0.69

ottest

0.66

ovie

0.65

âĢķ

0.65

ional

0.64

Activations Density 0.076%

phrases related to specific durations or time intervals

references to time periods, specifically the word "years" and its occurrences

No Known Activations