INDEX

Explanations

names of people and places

oai_token-act-pair · gpt-3.5-turbo

situations involving decisions or actions taken by individuals 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 resolutions

-0.69

 selves

-0.69

 respondents

-0.68

cellaneous

-0.65

 intervals

-0.59

 respondent

-0.58

arser

-0.58

 issu

-0.57

 Consumers

-0.56

 unison

-0.55

POSITIVE LOGITS

 assassinated

0.80

iership

0.74

ukemia

0.74

 Himself

0.68

 someday

0.68

die

0.67

 himself

0.67

NBA

0.66

 vocals

0.62

his

0.61

Activations Density 0.863%

names of people and places

situations involving decisions or actions taken by individuals in various contexts

No Comments

No Known Activations