INDEX

Explanations

proper nouns related to individuals

oai_token-act-pair · gpt-3.5-turbo

references to specific individuals, particularly those with the last name "Morrison."

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

-0.82

fare

-0.77

lihood

-0.76

cipline

-0.72

pread

-0.72

UAL

-0.71

fighter

-0.70

ggle

-0.67

teen

-0.67

kered

-0.67

POSITIVE LOGITS

 Leilan

0.82

 Morrison

0.82

rison

0.79

 Beans

0.76

shire

0.75

quist

0.73

edin

0.70

ufact

0.69

inez

0.69

igans

0.68

Activations Density 0.021%

proper nouns related to individuals

references to specific individuals, particularly those with the last name "Morrison."

No Comments

No Known Activations