INDEX

Explanations

phrases related to experiences and interactions over time

oai_token-act-pair · gpt-3.5-turbo

references to years of experience and contributions in a collaborative context

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

ives

-0.65

eness

-0.64

cock

-0.62

orescence

-0.60

ariat

-0.57

tumblr

-0.57

nikov

-0.55

verett

-0.55

iquid

-0.55

hoe

-0.54

POSITIVE LOGITS

viz

0.72

é¾įå¥ĳå£«

0.69

 ancestors

0.60

)]

0.60

luster

0.59

 previous

0.59

 predecessors

0.57

 kitchens

0.57

 occasions

0.57

 prior

0.57

Activations Density 0.912%

phrases related to experiences and interactions over time

references to years of experience and contributions in a collaborative context

No Comments

No Known Activations