INDEX

Explanations

phrases related to different groups or communities

oai_token-act-pair · gpt-3.5-turbo

references to the concept of community or groups within a specific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 prol

-0.74

oldemort

-0.71

emb

-0.71

chio

-0.69

di

-0.67

hod

-0.67

ivers

-0.66

oulos

-0.66

iris

-0.65

Clar

-0.65

POSITIVE LOGITS

 peers

0.81

 whom

0.79

Īè

0.77

 them

0.74

 those

0.74

warts

0.73

us

0.71

 onlook

0.70

among

0.70

wart

0.68

Activations Density 0.029%

phrases related to different groups or communities

references to the concept of community or groups within a specific context

No Comments

No Known Activations