INDEX

Explanations

concepts related to personal experiences and emotions felt by the narrator

oai_token-act-pair · gpt-3.5-turbo

references to personal feelings and experiences

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

earchers

-0.64

idth

-0.64

STA

-0.63

rising

-0.61

hovah

-0.58

 Larson

-0.57

 Door

-0.57

MN

-0.57

 Circuit

-0.56

ELY

-0.55

POSITIVE LOGITS

 realize

0.90

 feel

0.86

 accountable

0.83

 realise

0.80

 hesitate

0.79

 look

0.79

 reconsider

0.78

 forget

0.77

 ineligible

0.76

 disappear

0.75

Activations Density 0.061%

concepts related to personal experiences and emotions felt by the narrator

references to personal feelings and experiences

No Comments

No Known Activations