INDEX

Explanations

phrases indicating support or refutation of ideas or claims

oai_token-act-pair · gpt-3.5-turbo

discussions related to debunking myths or unsupported claims

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

ufact

-0.85

 actionGroup

-0.73

 unfocusedRange

-0.67

itaire

-0.67

rha

-0.66

ophon

-0.66

icult

-0.65

oided

-0.65

ishable

-0.64

Suc

-0.64

POSITIVE LOGITS

 assertions

1.62

 claims

1.56

 claim

1.48

 assertion

1.47

 hypotheses

1.42

 accusations

1.37

 notion

1.35

 allegation

1.35

 assumptions

1.35

 allegations

1.33

Activations Density 0.573%

phrases indicating support or refutation of ideas or claims

discussions related to debunking myths or unsupported claims

No Comments

No Known Activations