INDEX

Explanations

technology-related terms or brand names

oai_token-act-pair · gpt-3.5-turbo

references to "Neo" and related concepts or themes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

loo

-0.94

ãĤ¼ãĤ¦ãĤ¹

-0.92

 ILCS

-0.84

hips

-0.75

Reviewer

-0.74

tons

-0.74

rier

-0.72

ÑĮ

-0.71

rawdownloadcloneembedreportprint

-0.71

ional

-0.70

POSITIVE LOGITS

Geo

0.93

lect

0.77

clud

0.77

arthed

0.76

arest

0.75

Tok

0.72

 Scotia

0.70

 Enterprises

0.69

urnal

0.69

Pok

0.68

Activations Density 0.008%

technology-related terms or brand names

references to "Neo" and related concepts or themes

No Comments

No Known Activations