INDEX

Explanations

phrases with the word "in" followed by a number, potentially related to locations, rankings, or emphasis on specific quantities

oai_token-act-pair · gpt-3.5-turbo

phrases centered around the word "in" or its derivatives

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

 Seym

-0.84

ADRA

-0.76

anasia

-0.73

 vanquished

-0.72

 Annotations

-0.69

untled

-0.68

ESCO

-0.64

 mosqu

-0.63

OTOS

-0.61

 Advertisement

-0.60

POSITIVE LOGITS

tha

1.00

\'

0.84

ng

0.82

ta

0.81

wards

0.81

selves

0.80

 gonna

0.80

clusive

0.78

atin

0.77

cludes

0.75

Activations Density 0.063%

phrases with the word "in" followed by a number, potentially related to locations, rankings, or emphasis on specific quantities

phrases centered around the word "in" or its derivatives

No Comments

No Known Activations