INDEX

Explanations

instances of the word 'laid'

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "laid" 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 @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

Guard

-0.79

é¾įå

-0.78

obs

-0.78

ively

-0.72

antly

-0.72

=-=-=-=-=-=-=-=-

-0.69

 Defenders

-0.68

ities

-0.68

qua

-0.68

arta

-0.67

POSITIVE LOGITS

 laid

0.95

 showc

0.91

 arrang

0.87

sheets

0.81

 horizont

0.80

ayer

0.77

 groundwork

0.76

ndra

0.75

 encour

0.74

 WARN

0.72

Activations Density 0.010%

instances of the word 'laid'

occurrences of the word "laid" in various contexts

No Comments

No Known Activations