INDEX

Explanations

instances where information or plans are presented or given to someone

oai_token-act-pair · gpt-3.5-turbo

instances of the word "presented" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

umph

-0.71

 msec

-0.68

leen

-0.64

 corps

-0.64

tery

-0.62

ijn

-0.61

hene

-0.61

hovah

-0.61

 leak

-0.60

 churn

-0.59

POSITIVE LOGITS

icts

0.87

ENTS

0.79

ICT

0.79

 presentations

0.77

ATIVE

0.77

encing

0.77

 Present

0.76

iments

0.76

 presents

0.75

present

0.74

Activations Density 0.044%

instances where information or plans are presented or given to someone

instances of the word "presented" and its variations

No Comments

No Known Activations