INDEX

Explanations

vague and ambiguous language

oai_token-act-pair · gpt-3.5-turbo

terms related to ambiguity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

-0.85

Reviewer

-0.77

hers

-0.76

nea

-0.75

iseum

-0.70

Drive

-0.70

tes

-0.69

tackle

-0.67

tha

-0.66

ians

-0.65

POSITIVE LOGITS

 notions

0.87

neb

0.84

 recollection

0.83

 wording

0.82

 outlines

0.81

ures

0.80

 hints

0.76

 outline

0.75

 ceasefire

0.75

phr

0.73

Activations Density 0.051%

vague and ambiguous language

terms related to ambiguity

No Comments

No Known Activations