INDEX

Explanations

words related to identification or categorization

oai_token-act-pair · gpt-3.5-turbo

instances of the word "identify"

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

orld

-0.82

imeo

-0.76

bare

-0.74

perty

-0.71

 raining

-0.70

uden

-0.69

uss

-0.67

 beating

-0.66

 rejoice

-0.65

nuts

-0.65

POSITIVE LOGITS

ãĤ©

0.94

 identifies

0.84

 Identification

0.84

identified

0.82

 identification

0.80

 identifiers

0.79

 Ident

0.78

IDs

0.77

 identifying

0.75

ãĤ¿

0.75

Activations Density 0.029%

words related to identification or categorization

instances of the word "identify"

No Comments

No Known Activations