INDEX

Explanations

personal experiences or reflections

oai_token-act-pair · gpt-3.5-turbo

references to personal experiences or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

oplan

-0.65

oway

-0.63

orum

-0.63

quartered

-0.62

worth

-0.61

ten

-0.59

antis

-0.58

ilty

-0.57

PRES

-0.57

DERR

-0.56

POSITIVE LOGITS

 abruptly

0.85

 proceeded

0.84

 recons

0.83

 helicop

0.78

uddenly

0.72

 mysteriously

0.70

vo

0.68

 disappears

0.68

 swoop

0.67

 scapego

0.66

Activations Density 0.209%

personal experiences or reflections

references to personal experiences or actions

No Comments

No Known Activations