INDEX

Explanations

words related to different worlds or alternate realities

oai_token-act-pair · gpt-3.5-turbo

references to different worlds or settings within a narrative context

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ippi

-0.93

ifer

-0.82

oug

-0.79

odox

-0.76

icer

-0.73

 actionGroup

-0.73

etsk

-0.73

indal

-0.70

ibility

-0.70

veyard

-0.70

POSITIVE LOGITS

building

1.04

liness

0.96

wide

0.86

scape

0.84

views

0.80

 domination

0.75

fare

0.75

builders

0.71

places

0.70

 traveler

0.70

Activations Density 0.056%

words related to different worlds or alternate realities

references to different worlds or settings within a narrative context

No Comments

No Known Activations