INDEX

Explanations

news sources or publications

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "The" and associated news sources or identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 "$:/

-0.85

isSpecialOrderable

-0.80

=>

-0.66

 brakes

-0.65

 beds

-0.65

itatively

-0.64

ulators

-0.61

 silence

-0.61

 screws

-0.60

stood

-0.59

POSITIVE LOGITS

utterstock

1.35

alyst

0.89

imedia

0.89

intendent

0.83

 Images

0.82

senal

0.81

hesda

0.80

GoldMagikarp

0.77

Photo

0.76

lando

0.76

Activations Density 0.071%

news sources or publications

occurrences of the word "The" and associated news sources or identifiers

No Comments

No Known Activations