INDEX

Explanations

words related to interpersonal relationships, specifically actions related to interactions between individuals

oai_token-act-pair · gpt-3.5-turbo

references to interpersonal relationships and interactions involving "each other."

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

thouse

-0.69

ory

-0.61

ģ

-0.61

 Illustrated

-0.60

-0.58

 turnaround

-0.58

 Gale

-0.57

cit

-0.57

nit

-0.56

duc

-0.56

POSITIVE LOGITS

worldly

1.22

selves

0.86

 mutually

0.77

wise

0.75

 equally

0.70

 mate

0.69

bage

0.66

lings

0.66

's

0.64

 throats

0.63

Activations Density 0.034%

words related to interpersonal relationships, specifically actions related to interactions between individuals

references to interpersonal relationships and interactions involving "each other."

No Comments

No Known Activations