INDEX

Explanations

words related to specific medical treatments

oai_token-act-pair · gpt-3.5-turbo

specific names or terms related to individuals and entities

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

secut

-0.80

oses

-0.79

secution

-0.79

icles

-0.76

ctic

-0.71

ographer

-0.70

ographers

-0.69

atoes

-0.68

icer

-0.68

icular

-0.67

POSITIVE LOGITS

 Lans

0.83

%%

0.81

abwe

0.80

 Canaver

0.73

raft

0.72

eners

0.72

regate

0.70

lasses

0.68

 Fein

0.68

%%%%

0.65

Activations Density 0.041%

words related to specific medical treatments

specific names or terms related to individuals and entities

No Comments

No Known Activations