INDEX

Explanations

references to disorder or confusion

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "chaos" and its associated themes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

onga

-0.78

sburgh

-0.75

ĻĤ

-0.68

glas

-0.66

haps

-0.65

helps

-0.64

icrobial

-0.64

pointers

-0.63

OSP

-0.62

 Tanaka

-0.62

POSITIVE LOGITS

 ensued

1.09

 engulf

0.97

 havoc

0.92

 unfold

0.92

 disorder

0.88

 surrounding

0.86

INESS

0.85

 wrought

0.84

 chaos

0.83

ens

0.81

Activations Density 0.089%

references to disorder or confusion

occurrences of the word "chaos" and its associated themes

No Comments

No Known Activations