INDEX

Explanations

words related to time or sequence

oai_token-act-pair · gpt-3.5-turbo

the word "then" indicating a reference to a past time or context

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

toe

-0.77

assed

-0.72

ting

-0.67

ciplinary

-0.62

pace

-0.59

Winged

-0.58

icles

-0.58

ility

-0.58

ications

-0.57

cott

-0.57

POSITIVE LOGITS

Ń·

0.91

emort

0.72

orthy

0.71

ratulations

0.68

©¶æ

0.67

 unfocusedRange

0.66

abouts

0.66

esar

0.66

ð

0.65

å§«

0.65

Activations Density 0.048%

words related to time or sequence

the word "then" indicating a reference to a past time or context

No Comments

No Known Activations