INDEX

Explanations

every instance of the word "exactly"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "exactly" to emphasize precision or specificity in statements

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

ker

-0.80

rug

-0.77

rift

-0.76

olyn

-0.73

 sacrific

-0.65

asta

-0.64

kers

-0.64

cler

-0.63

gers

-0.63

isson

-0.63

POSITIVE LOGITS

 opposite

0.74

ãĤ¨

0.73

 wrong

0.72

ãĥ´ãĤ¡

0.67

 aligned

0.67

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

0.65

æ©Ł

0.65

 suited

0.63

ÃĽ

0.63

 tuned

0.62

Activations Density 0.014%

every instance of the word "exactly"

instances of the word "exactly" to emphasize precision or specificity in statements

No Comments

No Known Activations