INDEX

Explanations

phrases related to reasoning, explanation or justification

oai_token-act-pair · gpt-3.5-turbo

key reasons or explanations for events and situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ignty

-0.63

 feasibility

-0.61

 concedes

-0.60

 equivalents

-0.59

iggins

-0.58

iewicz

-0.57

 goodwill

-0.57

 realization

-0.56

jri

-0.56

 sqor

-0.56

POSITIVE LOGITS

so

0.78

 Matters

0.77

ãĤ»

0.75

Reviewer

0.70

videos

0.69

 persist

0.68

 bother

0.66

ItemImage

0.66

è¡

0.65

so

0.65

Activations Density 0.375%

phrases related to reasoning, explanation or justification

key reasons or explanations for events and situations

No Comments

No Known Activations