INDEX

Explanations

occurrences of the word "hand"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "hand" in various contexts

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

MSN

-0.71

acus

-0.67

 Seeking

-0.65

ashtra

-0.65

earances

-0.64

 Atmosp

-0.63

microsoft

-0.63

 Prediction

-0.62

âĨĳ

-0.62

 contradictions

-0.62

POSITIVE LOGITS

ily

0.94

picked

0.82

maid

0.81

bag

0.80

shake

0.79

knife

0.77

otom

0.76

sembly

0.73

 sacrific

0.72

bags

0.70

Activations Density 0.027%

occurrences of the word "hand"

instances of the word "hand" in various contexts

No Comments

No Known Activations