INDEX

Explanations

words containing the prefix "un-" or "unp-"

oai_token-act-pair · gpt-3.5-turbo

words prefixed with "un" that denote negation or an absence of quality

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Origins

-0.71

 Confederacy

-0.66

auga

-0.66

 Lauder

-0.65

 immersion

-0.65

ornia

-0.64

 Gazette

-0.64

Spa

-0.63

 Nanto

-0.62

 Rams

-0.61

POSITIVE LOGITS

ported

1.11

modified

0.98

leased

0.97

ipolar

0.95

assuming

0.95

ufact

0.92

numbered

0.91

structed

0.91

stretched

0.90

ruly

0.90

Activations Density 0.037%

words containing the prefix "un-" or "unp-"

words prefixed with "un" that denote negation or an absence of quality

No Comments

No Known Activations