INDEX

Explanations

titles or positions of authority

oai_token-act-pair · gpt-3.5-turbo

titles or roles associated with individuals in positions of authority or governance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

uld

-0.72

acters

-0.66

tnc

-0.61

 freedoms

-0.60

âĵĺ

-0.60

IRE

-0.58

humans

-0.58

-+-+-+-+

-0.58

articles

-0.57

ravings

-0.57

POSITIVE LOGITS

 overseeing

0.95

 extraord

0.90

 whom

0.77

 tasked

0.76

itol

0.73

 credited

0.71

 responsible

0.70

who

0.67

 entrusted

0.67

 presiding

0.67

Activations Density 0.174%

titles or positions of authority

titles or roles associated with individuals in positions of authority or governance

No Comments

No Known Activations