INDEX

Explanations

names of individuals or entities, potentially related to sports or technology

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names and specific terms

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

itudes

-0.80

sburgh

-0.79

ament

-0.69

ulators

-0.68

ambo

-0.67

akia

-0.67

andise

-0.65

izations

-0.63

essional

-0.63

ships

-0.63

POSITIVE LOGITS

cember

0.90

ynamic

0.83

etermin

0.81

etermination

0.81

ynam

0.80

hyde

0.78

ependent

0.77

iscovery

0.77

ysis

0.73

iamond

0.73

Activations Density 0.201%

names of individuals or entities, potentially related to sports or technology

proper nouns, particularly names and specific terms

No Comments

No Known Activations