INDEX

Explanations

phrases related to a previous knowledge or predictions

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "knew."

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

otion

-0.77

orio

-0.73

phrine

-0.72

adies

-0.72

pmwiki

-0.70

ItemTracker

-0.70

otos

-0.68

adish

-0.68

psey

-0.67

pex

-0.66

POSITIVE LOGITS

 beforehand

1.07

 instinctively

0.94

 nothing

0.76

nothing

0.74

lege

0.73

ledged

0.72

footed

0.70

bones

0.69

 firsthand

0.67

ledge

0.67

Activations Density 0.064%

phrases related to a previous knowledge or predictions

occurrences of the word "knew."

No Comments

No Known Activations