INDEX

Explanations

phrases indicating mutual interaction or support between entities

oai_token-act-pair · gpt-3.5-turbo

references to interpersonal relationships and interactions

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

uci

-0.70

cribed

-0.62

ession

-0.61

°

-0.60

ricia

-0.57

 majority

-0.56

 surgery

-0.55

 Majority

-0.55

 omission

-0.55

thouse

-0.55

POSITIVE LOGITS

worldly

1.12

selves

0.86

 mutually

0.74

's

0.73

opausal

0.71

stretched

0.71

 throats

0.69

ages

0.69

ickers

0.69

ymes

0.68

Activations Density 0.030%

phrases indicating mutual interaction or support between entities

references to interpersonal relationships and interactions

No Comments

No Known Activations