INDEX

Explanations

lists or enumerations

oai_token-act-pair · gpt-3.5-turbo

references to individuals or entities involved in security or investigation contexts

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

.ï¿½

-0.96

.''

-0.96

.</

-0.84

.ãĢį

-0.83

.''.

-0.82

."

-0.82

.'"

-0.81

ãĢĤ

-0.76

.","

-0.76

))))

-0.72

POSITIVE LOGITS

raq

0.72

rar

0.67

alys

0.67

staking

0.65

ileaks

0.63

osponsors

0.61

 confidential

0.61

coded

0.60

uine

0.59

 authorised

0.59

Activations Density 1.713%

lists or enumerations

references to individuals or entities involved in security or investigation contexts

No Comments

No Known Activations