INDEX

Explanations

the word "Bobby" with high activation values

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Bobby."

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

ered

-0.69

ASC

-0.68

liness

-0.68

perse

-0.65

PF

-0.64

absolute

-0.62

ering

-0.61

 confidential

-0.60

gypt

-0.60

restricted

-0.58

POSITIVE LOGITS

ging

0.93

 Jindal

0.88

rick

0.85

gee

0.84

selage

0.83

 Fischer

0.82

XVI

0.80

rill

0.77

gers

0.75

 Bobby

0.74

Activations Density 0.011%

the word "Bobby" with high activation values

occurrences of the name "Bobby."

No Comments

No Known Activations