INDEX

Explanations

words related to legitimacy or validation

oai_token-act-pair · gpt-3.5-turbo

terms related to legitimacy and its varying degrees in social and political contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 Horton

-0.70

rug

-0.69

berry

-0.69

ker

-0.68

king

-0.68

lla

-0.68

kers

-0.67

thus

-0.67

 Bend

-0.66

llo

-0.66

POSITIVE LOGITS

 legitimacy

1.18

 legitim

0.98

 Seym

0.94

itimate

0.94

istry

0.90

acies

0.85

 legality

0.83

 validity

0.82

clinton

0.82

 credentials

0.81

Activations Density 0.008%

words related to legitimacy or validation

terms related to legitimacy and its varying degrees in social and political contexts

No Comments

No Known Activations