INDEX

Explanations

proper nouns, specifically names of people and locations

oai_token-act-pair · gpt-3.5-turbo

instances of individuals and their associated details or identifiers in a narrative context

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ensical

-0.68

ulous

-0.65

 roundup

-0.62

waves

-0.62

isphere

-0.61

antics

-0.60

 ital

-0.60

oline

-0.60

parency

-0.59

 conclusions

-0.58

POSITIVE LOGITS

Jr

0.98

0.97

0.95

0.92

0.91

0.90

Activations Density 0.192%

proper nouns, specifically names of people and locations

instances of individuals and their associated details or identifiers in a narrative context

No Comments

No Known Activations