INDEX

Explanations

mentions of podcasts

oai_token-act-pair · gpt-3.5-turbo

punctuation and structure in written content

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

Lv

-0.74

 contradictory

-0.66

 weak

-0.66

Newsletter

-0.65

['

-0.65

 unspecified

-0.65

ocry

-0.65

SpaceEngineers

-0.64

 fide

-0.64

___

-0.63

POSITIVE LOGITS

LLC

1.07

podcast

1.02

Inc

0.85

 podcasts

0.79

creator

0.79

LLP

0.79

 creator

0.78

 Podcast

0.78

 creators

0.76

 curated

0.76

Activations Density 0.331%

mentions of podcasts

punctuation and structure in written content

No Comments

No Known Activations