INDEX

Explanations

words related to interpersonal relationships and interactions between people

oai_token-act-pair · gpt-3.5-turbo

references to relationships and social groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

cer

-0.80

 Kuala

-0.64

 bilateral

-0.61

aton

-0.60

BN

-0.57

du

-0.57

sum

-0.56

cos

-0.56

 signage

-0.55

ray

-0.55

POSITIVE LOGITS

 selves

1.03

hip

0.98

folk

0.98

hips

0.93

ervative

0.91

mates

0.87

heet

0.81

mith

0.80

 counterparts

0.77

ystem

0.77

Activations Density 0.145%

words related to interpersonal relationships and interactions between people

references to relationships and social groups

No Comments

No Known Activations