INDEX

Explanations

past tense verbs in the context of events or actions that were never completed

oai_token-act-pair · gpt-3.5-turbo

repetitions of the word "never."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ahime

-0.93

pour

-0.88

 antioxid

-0.84

iant

-0.69

tein

-0.66

achev

-0.66

 Tags

-0.63

åĤ

-0.61

imo

-0.61

emia

-0.60

POSITIVE LOGITS

theless

1.74

 bothered

1.16

 ceases

1.06

 dreamed

1.01

mind

0.97

 bothers

0.92

 ceased

0.90

 imagined

0.89

 EVER

0.87

 heard

0.85

Activations Density 0.057%

past tense verbs in the context of events or actions that were never completed

repetitions of the word "never."

No Comments

No Known Activations