INDEX

Explanations

verbs related to actions, achievements, and characteristics

oai_token-act-pair · gpt-3.5-turbo

action-oriented words related to providing, building, and understanding 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 @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

.)

-0.88

.]

-0.81

 nutshell

-0.74

emen

-0.67

âĢķ

-0.67

.)

-0.67

 âĢķ

-0.66

WAR

-0.61

SPONSORED

-0.60

POSITIVE LOGITS

agher

0.62

leanor

0.60

lete

0.57

lda

0.57

 Falk

0.56

utils

0.53

$,

0.53

agne

0.53

 Shogun

0.53

etc

0.53

Activations Density 0.461%

verbs related to actions, achievements, and characteristics

action-oriented words related to providing, building, and understanding in various contexts

No Comments

No Known Activations