INDEX

Explanations

phrases indicating possession or inclusion of something by individuals

oai_token-act-pair · gpt-3.5-turbo

instances of phrases indicating possession or alternate choices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 hazard

-0.62

 frust

-0.61

levard

-0.60

jug

-0.59

 Supplement

-0.58

sworth

-0.58

 hurd

-0.58

 reper

-0.57

ievers

-0.57

 manif

-0.55

POSITIVE LOGITS

own

0.87

senal

0.74

OWN

0.72

eenth

0.68

tre

0.67

internal

0.67

wikipedia

0.64

advertising

0.62

onian

0.62

 hers

0.62

Activations Density 0.135%

phrases indicating possession or inclusion of something by individuals

instances of phrases indicating possession or alternate choices

No Comments

No Known Activations