INDEX

Explanations

vague and nebulous language

oai_token-act-pair · gpt-3.5-turbo

terms and phrases indicating a lack of clarity or specificity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Reviewer

-0.79

din

-0.75

ICAN

-0.75

tes

-0.74

iseum

-0.74

tha

-0.72

oyal

-0.69

ournals

-0.69

vantage

-0.68

cano

-0.67

POSITIVE LOGITS

 vague

0.90

neb

0.88

ively

0.79

awa

0.78

 hints

0.74

abouts

0.74

 recollection

0.74

 ambig

0.73

 vaguely

0.72

 assurances

0.72

Activations Density 0.015%

vague and nebulous language

terms and phrases indicating a lack of clarity or specificity

No Comments

No Known Activations