INDEX

Explanations

dates specified in a particular format (for example, "June 20" expressed as "six/20")

oai_token-act-pair · gpt-3.5-turbo

specific dates related to events

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

orable

-0.73

ensed

-0.63

rw

-0.63

attled

-0.62

akespe

-0.61

wx

-0.60

 scissors

-0.59

edIn

-0.58

 loves

-0.57

 hygiene

-0.56

POSITIVE LOGITS

th

1.30

ths

0.89

TH

0.88

rd

0.85

teenth

0.82

 Forth

0.73

âĸĪâĸĪ

0.70

 onwards

0.68

eteenth

0.65

Activations Density 0.089%

dates specified in a particular format (for example, "June 20" expressed as "six/20")

specific dates related to events

No Comments

No Known Activations