INDEX

Explanations

words related to lack of clarity or uncertainty

oai_token-act-pair · gpt-3.5-turbo

terms related to vagueness and ambiguity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

din

-0.78

iseum

-0.71

nea

-0.69

Reviewer

-0.69

ICAN

-0.69

anza

-0.68

OF

-0.67

ienced

-0.66

tes

-0.66

hers

-0.66

POSITIVE LOGITS

 wording

0.89

neb

0.89

 recollection

0.83

 hints

0.77

ness

0.75

phr

0.75

 notions

0.74

 outlines

0.74

 outline

0.74

 hint

0.74

Activations Density 0.028%

words related to lack of clarity or uncertainty

terms related to vagueness and ambiguity

No Comments

No Known Activations