INDEX

Explanations

names of people or entities that are being recognized or awarded

oai_token-act-pair · gpt-3.5-turbo

the word "include" and its context within a list or examples

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ritic

-0.79

enser

-0.74

oler

-0.73

istical

-0.71

kin

-0.71

reading

-0.68

rites

-0.68

bis

-0.67

alloween

-0.67

dule

-0.66

POSITIVE LOGITS

:-

0.91

*:

0.89

Ala

0.85

0.80

:[

0.77

:(

0.75

:#

0.73

Flo

0.73

 Fernand

0.73

 Rudolph

0.72

Activations Density 0.209%

names of people or entities that are being recognized or awarded

the word "include" and its context within a list or examples

No Comments

No Known Activations