INDEX

Explanations

phrases where the speaker expresses personal opinions or experiences

oai_token-act-pair · gpt-3.5-turbo

phrases indicating personal experiences or opinions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 substitutes

-0.66

pires

-0.65

 Schwar

-0.61

matter

-0.58

 unfocusedRange

-0.58

 signals

-0.57

 surplus

-0.57

 resumes

-0.57

redients

-0.56

 disadvantages

-0.56

POSITIVE LOGITS

've

1.57

'm

1.12

'd

1.06

 ever

1.04

 know

0.98

RL

0.97

saw

0.96

 have

0.90

 encountered

0.90

 HAVE

0.90

Activations Density 0.071%

phrases where the speaker expresses personal opinions or experiences

phrases indicating personal experiences or opinions

No Comments

No Known Activations