INDEX

Explanations

names of individuals or entities

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names

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

lain

-0.73

INESS

-0.67

 glim

-0.65

 subp

-0.64

 Cosponsors

-0.64

 secretaries

-0.64

 princ

-0.64

 brightest

-0.62

 unfocusedRange

-0.61

 behavi

-0.60

POSITIVE LOGITS

onga

0.93

jit

0.92

ichi

0.91

qi

0.90

Plex

0.90

hi

0.89

qa

0.87

asa

0.86

udi

0.85

uthor

0.85

Activations Density 0.151%

names of individuals or entities

proper nouns, particularly names

No Comments

No Known Activations