INDEX

Explanations

references to the TV show "Doctor Who"

oai_token-act-pair · gpt-3.5-turbo

references to the television series "Doctor Who"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

rations

-0.96

ration

-0.72

rator

-0.68

çĶŁ

-0.66

pu

-0.65

rators

-0.65

ģ«

-0.63

rative

-0.62

Ä±

-0.61

âĸ¬

-0.60

POSITIVE LOGITS

soever

1.15

abouts

0.77

oping

0.76

pedia

0.73

verse

0.72

iw

0.71

ipedia

0.71

icide

0.71

ÃŃs

0.70

oped

0.70

Activations Density 0.016%

references to the TV show "Doctor Who"

references to the television series "Doctor Who"

No Comments

No Known Activations