INDEX

Explanations

mentions of past events

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "past" in various contexts

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

anguage

-0.78

shapeshifter

-0.72

Software

-0.69

Downloadha

-0.68

hyde

-0.68

tyard

-0.67

hz

-0.66

Reply

-0.64

zhen

-0.64

Dev

-0.63

POSITIVE LOGITS

ebin

1.44

iche

0.89

 tense

0.88

ures

0.85

imes

0.74

 midnight

0.73

İ

0.73

ime

0.73

 generations

0.73

 week

0.72

Activations Density 0.024%

mentions of past events

references to the concept of "past" in various contexts

No Comments

No Known Activations